{ "complete": true, "report": { "bucket": "emo_Fatigue_Exhaustion", "label": "Intense Fatigue Exhaustion", "definition": { "id": "emo_Fatigue_Exhaustion", "category": "emotion", "head": "emo_Fatigue_Exhaustion", "pole": "high", "label": "Intense Fatigue Exhaustion", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_fatigue_exhaustion/full-v2-sealed/sealed-selected", "mission": "emotion_fatigue_exhaustion", "format_status": "CANONICAL", "heldout": true, "qualified": false, "source_cfg": 3, "source_model": { "label": "Humaneness 1.5 + real-speech rank 4", "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs", "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714", "rank": 4 }, "metrics": { "ce": 6.125908069610595, "genuineness": 4.54450129032135, "wer": 0.019787333508551528, "identity": 0.5869492122530937, "voiceclap": 0.011845211796462536, "fitness": 0.7725339049564964, "steering_v2": 0.8911804123200376, "raw_target": 1.6150949247181416, "target_cdf": 0.8911804123200376, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.137305812835693, "genuineness": 4.552534599304199, "wer": 0.019100483548064193, "identity": 0.5869492122530937, "fitness": 0.7623136223390078, "steering_v2": 0.8681902728786123 }, "none": { "n": 50, "ce": 6.114510326385498, "genuineness": 4.536467981338501, "wer": 0.020474183469038863, "identity": null, "fitness": 0.782754187573985, "steering_v2": 0.914170551761463 } } } } ], "selected_wording": { "id": "manual-1711f3012766", "general": "Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.", "inline": [ "Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.", "Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.", "Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking." ], "cfg": 3, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 4.494531336365252, "target_raw": 2.713350784778595, "ce": 5.546400880813598, "genuineness": 4.53684446811676, "identity": 0.5492007732391357, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.003564983606338501, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 4.835546991459625, "target_raw": 2.897770071029663, "ce": 5.242345452308655, "genuineness": 4.421051549911499, "identity": 0.5263246513903141, "wer": 0.048539516683866524, "valid_fraction": 0.9, "identity_delta": -0.02644110545516014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 4.494531336365252, "target_raw": 2.713350784778595, "ce": 5.546400880813598, "genuineness": 4.53684446811676, "identity": 0.5492007732391357, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.003564983606338501, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 3.9718750788739494, "target_raw": 2.4307013154029846, "ce": 5.697956919670105, "genuineness": 4.620002031326294, "identity": 0.5649965524673461, "wer": 0.009399509803921569, "valid_fraction": 1, "identity_delta": 0.012230795621871949, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 3.504541078434625, "target_raw": 2.1779698014259337, "ce": 5.90426778793335, "genuineness": 4.6444785594940186, "identity": 0.5608148440718651, "wer": 0.022001848985208117, "valid_fraction": 0.95, "identity_delta": 0.008049087226390838, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 2.5334961158471914, "target_raw": 1.6528343237936496, "ce": 5.950732469558716, "genuineness": 4.61247079372406, "identity": 0.6007044404745102, "wer": 0.03335053319573443, "valid_fraction": 0.9, "identity_delta": 0.04793868362903595, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.774218752497101, "target_raw": 1.2422215342521667, "ce": 6.026386356353759, "genuineness": 4.581090641021729, "identity": 0.6000490859150887, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.04728332906961441, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 1.5238281273679406, "target_raw": 1.1068117380142213, "ce": 6.046838736534118, "genuineness": 4.582031989097596, "identity": 0.612480778992176, "wer": 0.009298245614035087, "valid_fraction": 1, "identity_delta": 0.05971502214670181, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 1.0405761556707518, "target_raw": 0.845471877604723, "ce": 6.126464056968689, "genuineness": 4.512367916107178, "identity": 0.5912722155451775, "wer": 0.01067251461988304, "valid_fraction": 0.95, "identity_delta": 0.03850645869970322, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 4.853125061652563, "target_raw": 2.90727618932724, "ce": 5.367790031433105, "genuineness": 4.451804184913636, "identity": 0.4628649616613984, "wer": 0.07342728758169935, "valid_fraction": 0.85, "identity_delta": -0.08990079518407583, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 4.835546991459625, "target_raw": 2.897770071029663, "ce": 5.242345452308655, "genuineness": 4.421051549911499, "identity": 0.5263246513903141, "wer": 0.048539516683866524, "valid_fraction": 0.9, "identity_delta": -0.02644110545516014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 4.76992192567393, "target_raw": 2.8622804164886473, "ce": 5.2943203210830685, "genuineness": 4.379315865039826, "identity": 0.5188866212964058, "wer": 0.027687908496732024, "valid_fraction": 1, "identity_delta": -0.03387913554906845, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 4.5140625597582105, "target_raw": 2.7239131569862365, "ce": 5.470796585083008, "genuineness": 4.518016362190247, "identity": 0.5393436491489411, "wer": 0.025464181286549707, "valid_fraction": 0.95, "identity_delta": -0.013422107696533203, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 4.389062595578694, "target_raw": 2.656313902139664, "ce": 5.547244715690613, "genuineness": 4.543434357643127, "identity": 0.58019197024405, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": 0.02742621339857578, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 4.20615245737886, "target_raw": 2.55739716142416, "ce": 5.409588360786438, "genuineness": 4.461845827102661, "identity": 0.5274524688720703, "wer": 0.022748538011695907, "valid_fraction": 0.95, "identity_delta": -0.02531328797340393, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 3.870898507784783, "target_raw": 2.3760937720537187, "ce": 5.706197452545166, "genuineness": 4.586425232887268, "identity": 0.5744536362588406, "wer": 0.011165935672514619, "valid_fraction": 1, "identity_delta": 0.021687879413366317, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 3.640185622848222, "target_raw": 2.251325583457947, "ce": 5.641563987731933, "genuineness": 4.581718254089355, "identity": 0.6183966718614101, "wer": 0.005572755417956656, "valid_fraction": 1, "identity_delta": 0.0656309150159359, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 3.4535156757600363, "target_raw": 2.150375559926033, "ce": 5.822259736061096, "genuineness": 4.609960341453553, "identity": 0.5765532955527306, "wer": 0.011374269005847953, "valid_fraction": 1, "identity_delta": 0.023787538707256316, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 3.3854004526166093, "target_raw": 2.1135392427444457, "ce": 5.686241507530212, "genuineness": 4.595525431632995, "identity": 0.5376642979681492, "wer": 0.010818713450292398, "valid_fraction": 1, "identity_delta": -0.015101458877325058, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 3.3558106721013874, "target_raw": 2.097537261247635, "ce": 5.643251824378967, "genuineness": 4.52554759979248, "identity": 0.5614721298217773, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.008706372976303101, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 3.268164133258371, "target_raw": 2.050138521939516, "ce": 5.757526922225952, "genuineness": 4.5845424175262455, "identity": 0.6023450806736946, "wer": 0.013906088751289989, "valid_fraction": 0.95, "identity_delta": 0.04957932382822037, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 2.8413574954802816, "target_raw": 1.8193239703774453, "ce": 5.939017009735108, "genuineness": 4.589249396324158, "identity": 0.5525884442031384, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.00017731264233589172, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 2.7544433987312495, "target_raw": 1.7723213315010071, "ce": 5.929882907867432, "genuineness": 4.613412189483642, "identity": 0.5658502623438835, "wer": 0.013450292397660818, "valid_fraction": 1, "identity_delta": 0.013084505498409272, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 2.642480504839568, "target_raw": 1.7117724485695363, "ce": 5.92551441192627, "genuineness": 4.607136130332947, "identity": 0.5405524425208569, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.012213314324617386, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 2.076074209461215, "target_raw": 1.4054632127285003, "ce": 6.028967690467835, "genuineness": 4.587680435180664, "identity": 0.5578112408518792, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.005045484006404877, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.7852050876990144, "target_raw": 1.248162880539894, "ce": 6.030556273460388, "genuineness": 4.57920777797699, "identity": 0.5629164800047874, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.010150723159313202, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.6337402379538193, "target_raw": 1.1662515692412854, "ce": 6.057561326026916, "genuineness": 4.545630955696106, "identity": 0.5556108526885509, "wer": 0.006274509803921568, "valid_fraction": 1, "identity_delta": 0.002845095843076706, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.6302246462341485, "target_raw": 1.1643503576517105, "ce": 6.087346339225769, "genuineness": 4.584228587150574, "identity": 0.5573355346918106, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.004569777846336364, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.4014648580114606, "target_raw": 1.0406383924186229, "ce": 6.0738438129425045, "genuineness": 4.550651788711548, "identity": 0.5564877301454544, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": 0.0037219732999801635, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 1.2598876865269022, "target_raw": 0.9640742801129818, "ce": 6.152674865722656, "genuineness": 4.5748146057128904, "identity": 0.5764253735542297, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": 0.023659616708755493, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 1.1657226752258152, "target_raw": 0.9131503887474537, "ce": 6.140165162086487, "genuineness": 4.515819787979126, "identity": 0.557474835216999, "wer": 0.01112831097351221, "valid_fraction": 1, "identity_delta": 0.004709078371524811, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.1371826511809022, "target_raw": 0.8977161094546318, "ce": 6.002955532073974, "genuineness": 4.524920010566712, "identity": 0.5640393376350403, "wer": 0.02134502923976608, "valid_fraction": 0.95, "identity_delta": 0.01127358078956604, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 1.0857910336590204, "target_raw": 0.8699238210916519, "ce": 6.120904183387756, "genuineness": 4.493226003646851, "identity": 0.5695938974618912, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.01682814061641693, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 4.718750105394885, "target_raw": 2.8346069931983946, "ce": 5.321821856498718, "genuineness": 4.400654411315918, "identity": 0.4881782615557313, "wer": 0.05644736842105263, "valid_fraction": 0.8, "identity_delta": -0.06458749528974295, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.7193359631813924, "target_raw": 0.6717470467090607, "ce": 6.147114992141724, "genuineness": 4.440193462371826, "identity": 0.5527657568454742, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": 0.7667480475907639, "target_raw": 0.6973872266709804, "ce": 6.139768004417419, "genuineness": 4.46121826171875, "identity": 0.6022078529000282, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.049442096054553984, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.6671142610603458, "target_raw": 0.6435058534145355, "ce": 6.173127245903015, "genuineness": 4.46278725862503, "identity": 0.5752792730927467, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.02251351624727249, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.7963378749481567, "target_raw": 0.7133892334997654, "ce": 6.13023681640625, "genuineness": 4.396575021743774, "identity": 0.5661403596401214, "wer": 0.005902777777777778, "valid_fraction": 1, "identity_delta": 0.013374602794647217, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 0.22037109745475073, "target_raw": 0.40190974444150923, "ce": 6.218479900360108, "genuineness": 4.467933607101441, "identity": 0.6025339433550835, "wer": 0.012038396386222472, "valid_fraction": 0.98, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 3.9364063325765475, "target_raw": 2.4115200233459473, "ce": 5.727543363571167, "genuineness": 4.545254383087158, "identity": 0.584985556602478, "wer": 0.03419734613212874, "valid_fraction": 0.98, "identity_delta": -0.01754838675260544, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 4.0684375645113136, "target_raw": 2.482921746969223, "ce": 5.529473075866699, "genuineness": 4.4226205444335935, "identity": 0.5450114373862743, "wer": 0.06336152139241384, "valid_fraction": 0.92, "identity_delta": -0.057522505968809125, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 4.257656324172511, "target_raw": 2.585250153541565, "ce": 5.586183691024781, "genuineness": 4.446595048904419, "identity": 0.5242721079289914, "wer": 0.06323442994838875, "valid_fraction": 0.92, "identity_delta": -0.07826183542609215, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.1892187596611978, "ci95_z": [ -0.510468768891861, 0.12062499579798172 ], "language_deltas": { "en": -0.2867187125434849, "de": 0.3390625018943525, "fr": -0.0062500461533154805, "nl": -0.7531250285875014, "es": -0.23906251291603967 }, "languages_improved": 1, "clear_gain": false, "delta_ce": -0.056710615158081054, "delta_genuineness": -0.023974504470825195, "delta_wer": 0.0001270914440250835, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "adapter_vs_best_manual": { "n": 50, "delta_z": 0.13203123193476568, "ci95_z": [ -0.17515627705479803, 0.4303125320662213 ], "language_deltas": { "en": 0.38515628917865385, "de": 0.037499924225900115, "fr": 0.6109375036164911, "nl": -0.43281253289284805, "es": 0.059374975545631294 }, "languages_improved": 4, "clear_gain": false, "delta_ce": -0.19807028770446777, "delta_genuineness": -0.12263383865356445, "delta_wer": 0.0291641752602851, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 3.716035235121797, "ci95_z": [ 3.1425098123326287, 4.289560657910965 ], "language_deltas": { "en": 2.7689453463184974, "de": 3.5989747736724076, "fr": 3.2878417976768706, "nl": 4.517675849091499, "es": 4.4067384088497095 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.49093653678894045, "delta_genuineness": 0.07732077598571778, "delta_wer": 0.022158949745906268, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 4.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024287.0682292, "example": { "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "language": "es", "seed": 1702, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "0018a0737f91997feb91280c86924a43af85ecd47498275007c4a6461da9224c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "974bde574452486dc1e1332598d9b1a75d60e2a7ac1bff0ee2b8ab1d1231fce9", "generation_seconds_batch": 21.53121063800063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7622666954994202, "target_z": 0.886718767651921, "ce": 6.41180419921875, "genuineness": 4.469690799713135, "identity": 0.2000957429409027, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0018a0737f91997feb91280c86924a43af85ecd47498275007c4a6461da9224c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "003142cac74c92cbe03f6fb4a9da70e90200007ddb591239ec9ba5f4bf7d49b6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71618d8860b34b92e69f3a4812c359fc2e8a9673ecd458c2084d231dea33f7cd", "generation_seconds_batch": 21.087776396074332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4403719902038574, "target_z": 2.140625156714616, "ce": 5.696964263916016, "genuineness": 4.68307638168335, "identity": 0.7121602296829224, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/003142cac74c92cbe03f6fb4a9da70e90200007ddb591239ec9ba5f4bf7d49b6.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "004d8184d5a496a739fc164428cd42c43f6fd01a25fc7c3e29bc8786e3c46f5d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53768704a8c06b3edb6ffa3f741d70378e252332fbfa6c169bf7bb1c3ef2eed2", "generation_seconds_batch": 16.097745296079665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7361187934875488, "target_z": 2.687500117105427, "ce": 5.919358730316162, "genuineness": 4.406930446624756, "identity": 0.5173094272613525, "hypothesis": "Ik heb het een klein doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/004d8184d5a496a739fc164428cd42c43f6fd01a25fc7c3e29bc8786e3c46f5d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "0141e224584d978602a5837d621846e76225d219cd3e0599d455d047d2bdaf02", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c050c175e7f6b69c17e15c6fd62b83d09a57d4da89e4c59f3fa5c8f3f2c62de", "generation_seconds_batch": 16.933936109999195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767007827758789, "target_z": 4.593750306540677, "ce": 6.157639026641846, "genuineness": 4.632867813110352, "identity": 0.623336672782898, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0141e224584d978602a5837d621846e76225d219cd3e0599d455d047d2bdaf02.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "01497ba0a0f5dbb4d77633b46d0aaff475d3cf8396a0af0535e0c47d12a25359", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "645eccfac30676780ccf890c09f8f802897a496ca8d1f2961f3945b53db4a8d1", "generation_seconds_batch": 22.23410872905515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.711567223072052, "target_z": 0.7929687366534256, "ce": 6.0146708488464355, "genuineness": 4.545003414154053, "identity": 0.8003484606742859, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/01497ba0a0f5dbb4d77633b46d0aaff475d3cf8396a0af0535e0c47d12a25359.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "015dc2222b045c03b9b7aca9311cf0e0aec7f266f105ac169444804a722188a0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53ec533b4c8df74ac135f60b1561b89af7022cd3530f8376b28422b3e76868c4", "generation_seconds_batch": 22.131375003024004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767007827758789, "target_z": 4.593750306540677, "ce": 5.8875885009765625, "genuineness": 4.6705241203308105, "identity": 0.14357565343379974, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/015dc2222b045c03b9b7aca9311cf0e0aec7f266f105ac169444804a722188a0.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "01aae5fa127a8d87c60587e834d6ac6315f61355beb2043fcb8ec22f91d6efc7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83bd72d3ec881f091cecf60595d77204472aee5cefa568bedf1b801dd4e56f4e", "generation_seconds_batch": 21.85612337803468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.341601610183716, "target_z": 5.656250216989468, "ce": 5.895530700683594, "genuineness": 4.469690799713135, "identity": 0.3463861346244812, "hypothesis": "De de deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/01aae5fa127a8d87c60587e834d6ac6315f61355beb2043fcb8ec22f91d6efc7.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4bb4af32270affd9210ea7a6be437fef171788929b831455cfadfca446b38d3f", "generation_seconds_batch": 18.673215952003375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07148660719394684, "target_z": -0.39062499138930684, "ce": 6.09409761428833, "genuineness": 4.720732688903809, "identity": 0.7181038856506348, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis le bien et verifie the two dernier chiffres. Appelle-moi quand tu auras a moment.", "wer": 0.22727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "025669e8ace0ba7b7ff1fbdc33746f3814aa5986ca53bd92e6be74ad8081e282", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63772b696d6f4120b27038166e33d9b2bfa04e8357a109493659073aa30ada2d", "generation_seconds_batch": 19.87447129993234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.141714334487915, "target_z": 3.4374999242259, "ce": 5.704906940460205, "genuineness": 4.7332844734191895, "identity": 0.42178115248680115, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/025669e8ace0ba7b7ff1fbdc33746f3814aa5986ca53bd92e6be74ad8081e282.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "02784581fb4cadd4b52ca72d26b924a3745d2cb80c4f608d0e752cdaff68b0cb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dac1276ac60ef0afd179e1674fd6e36a2b20aa964688414d91ed0f94d5d0d6ac", "generation_seconds_batch": 22.838526348932646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.699408531188965, "target_z": 4.46875026520935, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.7201433181762695, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/02784581fb4cadd4b52ca72d26b924a3745d2cb80c4f608d0e752cdaff68b0cb.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "031b7249ab371f6f6294ebd552b199b6d4f7411e4941c8c2e41d3829a33748f0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "222a17bbf3b15c72c536659427d3113a9acd08ba265421fef0e99dbf5e97c3d5", "generation_seconds_batch": 21.08501213300042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34293994307518005, "target_z": 0.11132813425649517, "ce": 6.141753673553467, "genuineness": 4.65797233581543, "identity": 0.6270677447319031, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/031b7249ab371f6f6294ebd552b199b6d4f7411e4941c8c2e41d3829a33748f0.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "0376550ad80591b29d4771e96f13fa8f358a74ff2c6ac26762c187e12dbb787b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bf4f0e2011eac96bc7a4120e1d5ef8f636028c88b046299285779f4b96945c2", "generation_seconds_batch": 20.928502753959037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091014862060547, "target_z": 3.343749893227405, "ce": 5.593709468841553, "genuineness": 4.758388519287109, "identity": 0.7945876121520996, "hypothesis": "Me he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0376550ad80591b29d4771e96f13fa8f358a74ff2c6ac26762c187e12dbb787b.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "03a5569c3d56f604e8b31d0e5ff55b99ab7de408a2512b0c6986c4de730ed60b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5c13a5560969dcf15ce45794fa26280c1ac2f0a92c823162df2a65edb754b8f", "generation_seconds_batch": 16.60087605204899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.462655067443848, "genuineness": 4.419482707977295, "identity": 0.7455120086669922, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/03a5569c3d56f604e8b31d0e5ff55b99ab7de408a2512b0c6986c4de730ed60b.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "03b2c745456250d75d8ed338d634a14a2bb084005c74ec9649cc4cd8062a037f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e33f8dc092d941c0ff8cf8775750a0e724408279d7cfe8cabc0508cbc5cd8268", "generation_seconds_batch": 16.264868042082526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1488499641418457, "target_z": 1.6015623682563944, "ce": 6.23706579208374, "genuineness": 4.381826400756836, "identity": 0.5237534046173096, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/03b2c745456250d75d8ed338d634a14a2bb084005c74ec9649cc4cd8062a037f.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "03b8e12dc8fa846cc7cc170434bdfb78bcf3279a79f1302ed488fcd76ff151ab", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "25d15d20512ab2a7e40dc92cc3dea9b6d71d211b02b4f4a5fc2b6e3eee1a1da3", "generation_seconds_batch": 24.454453208949417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4205615520477295, "target_z": 3.9531253151513703, "ce": 5.673136234283447, "genuineness": 4.770940780639648, "identity": 0.7091740369796753, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, liß sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/03b8e12dc8fa846cc7cc170434bdfb78bcf3279a79f1302ed488fcd76ff151ab.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "03c009c6321ef622dd2e00ef9323a34b1bfdadf7606855560328e05edbf61eab", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dab68502a60e848c08578a323666492d2601cdc359c068813d38be4361584246", "generation_seconds_batch": 21.554764194064774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4205615520477295, "target_z": 3.9531253151513703, "ce": 5.081407070159912, "genuineness": 4.607763767242432, "identity": 0.7038967609405518, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/03c009c6321ef622dd2e00ef9323a34b1bfdadf7606855560328e05edbf61eab.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "0467a3a85955d8e930828c8272cc2656cef4eebac5a6648c746245acad20823d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3fab0620f1dda9911bb07aaeb41b648c045a1cf66847dee263c2e1cf6463e9f", "generation_seconds_batch": 16.09256077092141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46281099319458, "target_z": 4.031250120549704, "ce": 5.359400749206543, "genuineness": 4.482243061065674, "identity": 0.8712086081504822, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0467a3a85955d8e930828c8272cc2656cef4eebac5a6648c746245acad20823d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "0526f3d81602b208370c522f150c9522e6087268453e823711075fd50ddab73c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9039829f4602aa35dcadfe1ab00a9ee3b3c2629e1d48f5c7aeb4d10aa3eb5622", "generation_seconds_batch": 21.186873442027718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5079712867736816, "target_z": 2.265625198045943, "ce": 6.117925643920898, "genuineness": 4.821148872375488, "identity": 0.8202061653137207, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0526f3d81602b208370c522f150c9522e6087268453e823711075fd50ddab73c.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "0555c0b73d1bdfb3a26cc37a16494a8b7b69e7d4c71611f4bfa9f7041b28cb68", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "624372d8f76ac16cebdc56e96405ba6e12432f8ced24fa084079148387973bba", "generation_seconds_batch": 15.505738607957028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0825650691986084, "target_z": 3.328125108494734, "ce": 6.109982967376709, "genuineness": 4.570107460021973, "identity": 0.5049256086349487, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0555c0b73d1bdfb3a26cc37a16494a8b7b69e7d4c71611f4bfa9f7041b28cb68.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "055cd76df99128f9c179172ee36013e2852563f9c4ea721049b0eb0b94c35903", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac2d77840358f14788cbddd3fffb88dd4f0e79d39feaee991cd05a38f805ba78", "generation_seconds_batch": 22.361298772040755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9191060066223145, "target_z": 4.874999958668673, "ce": 5.371314525604248, "genuineness": 4.545003414154053, "identity": 0.5093672275543213, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/055cd76df99128f9c179172ee36013e2852563f9c4ea721049b0eb0b94c35903.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22758ac5e58591ec0697fd584d3911f38bd88a4b2268864a5456fab7fd85bf2c", "generation_seconds_batch": 17.625090943067335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4168766438961029, "target_z": 0.248046874354198, "ce": 6.340320587158203, "genuineness": 4.607763767242432, "identity": 0.519755482673645, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "05a9ff8ccd11b50ef33d1f0ce552880a666d41dfc204f38ab869e0e2ea5f00a7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cdc00494b93a041e4cf017f6e86d786e74edee00b276ca6375aa48708c4b582a", "generation_seconds_batch": 21.94367308798246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8488782644271851, "target_z": 1.0468750154992477, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.31072208285331726, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/05a9ff8ccd11b50ef33d1f0ce552880a666d41dfc204f38ab869e0e2ea5f00a7.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "05fbadab29ccf0218c91d1acbb7398bc57de962fbc5060ad5d3e70c611acc0a4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "166a8bb24b54f0a09e665270a818dea2b4d07d92c69e0401d90bda385e44eddf", "generation_seconds_batch": 23.063552314066328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0487654209136963, "target_z": 3.2656250878290702, "ce": 5.967014789581299, "genuineness": 4.3881025314331055, "identity": 0.6542299389839172, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/05fbadab29ccf0218c91d1acbb7398bc57de962fbc5060ad5d3e70c611acc0a4.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "06036e730f80ce8b8a6f4f934dc6918c5a49eeba1d663a2103fb8098a3f0936d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dcd10ccce011969a0424bd750a47cd9f83dc32dc0ee96a907afa2a1b3a70a6a", "generation_seconds_batch": 22.149881686083972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 5.847874641418457, "genuineness": 4.344170093536377, "identity": 0.6384199857711792, "hypothesis": "Ik heb het ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/06036e730f80ce8b8a6f4f934dc6918c5a49eeba1d663a2103fb8098a3f0936d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "06225809639fe2c78451b1cf2f5ee50d4e5b0ccc16400e284c94b2959417e5c9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "711472a31bd3cd6121dba2a2f25e18f4ba950eb23f691d06758eac39e463b9aa", "generation_seconds_batch": 15.707980022998527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28484681248664856, "target_z": 0.0039062512916039765, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.7398102283477783, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/06225809639fe2c78451b1cf2f5ee50d4e5b0ccc16400e284c94b2959417e5c9.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "06a1cd56bb25133e5c3d99590f4909d211f7ec92ec2c21052f0dc8088eac2750", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66720615e852ec3227554e0e767d97ecb527d4376448c78ad19cfeaebd6b7a91", "generation_seconds_batch": 21.54183263401501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.268462896347046, "target_z": 3.6718747812883934, "ce": 5.254160404205322, "genuineness": 4.381826400756836, "identity": 0.7210502624511719, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suche dir in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.19047619047619047, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/06a1cd56bb25133e5c3d99590f4909d211f7ec92ec2c21052f0dc8088eac2750.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "06eab42d164e61684a1e48531b34ecfacefd3bd47ec34d8e7cce9c14882eac5d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bda545dbf71dc640642c030b502033d83685098e788d61d6af6fc4497fe69c27", "generation_seconds_batch": 21.85612337803468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487090587615967, "target_z": 4.375000234210854, "ce": 5.919358730316162, "genuineness": 4.394378662109375, "identity": 0.7030950784683228, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/06eab42d164e61684a1e48531b34ecfacefd3bd47ec34d8e7cce9c14882eac5d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "07806550e93f8f3d9f5ff5066aab189b11a0ba5bb4ca65891fc26e2cac0cf785", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d92ee8bd5922a1efce9752e5971a979f2c98081c46d5eb780748ceeef73c86a", "generation_seconds_batch": 19.709864542004652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4319219589233398, "target_z": 2.1249999311144547, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.4350564479827881, "hypothesis": "The door is still open. I put your coat on the chair? Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/07806550e93f8f3d9f5ff5066aab189b11a0ba5bb4ca65891fc26e2cac0cf785.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "07d9090aa9627c544a7dacd47549b6f86360c0ba1b13381cb053a49463ef5842", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1acc4e489ea9aec192b220473c88ae458c9a6cef068d412e886e4a0eb2b8ad5", "generation_seconds_batch": 22.463190381997265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0403153896331787, "target_z": 3.249999862228909, "ce": 6.070269584655762, "genuineness": 4.432034492492676, "identity": 0.48574569821357727, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/07d9090aa9627c544a7dacd47549b6f86360c0ba1b13381cb053a49463ef5842.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "07f4fcb83f97b9a5226f092916467c321210430ed22c60611d28df407350b880", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9dbbdc8da6f0ce109e0835cfc8c701ff933dff665cba75b341d4d6b9e8b4869", "generation_seconds_batch": 21.32508586999029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487090587615967, "target_z": 4.375000234210854, "ce": 5.39911413192749, "genuineness": 4.469690799713135, "identity": 0.6979494094848633, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/07f4fcb83f97b9a5226f092916467c321210430ed22c60611d28df407350b880.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "0801f463966aa92156feeaba73bdee77ccdffa6548bbedd1b0ba0b626eb7b5a9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "425a7e1344cec968ede1b2d1863013e544fcd8def7d5bb55a49f27eda6c54a8e", "generation_seconds_batch": 16.177512650960125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479710817337036, "target_z": 4.062500130882536, "ce": 6.070269584655762, "genuineness": 5.009429931640625, "identity": 0.7822823524475098, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0801f463966aa92156feeaba73bdee77ccdffa6548bbedd1b0ba0b626eb7b5a9.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "082706c2fe30e0d523389ad11406871f555b92110dbfe62041911183cd4118f6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a2ec382a441a2612a5bbfc43873336594b5e17a5cc6afaa28b6aec3018d3bc7", "generation_seconds_batch": 20.626726294052787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5417709350585938, "target_z": 2.3281252187116066, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.41845834255218506, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/082706c2fe30e0d523389ad11406871f555b92110dbfe62041911183cd4118f6.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "086afe8442294266a6913ad49e82d58c406363ee9d56effcc7890dae5c87518a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e12ca444a9d0cc4a88051dbb18865f2c91651563feeb9b53facbb4db3523f2c", "generation_seconds_batch": 20.901350981090218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 5.824047088623047, "genuineness": 4.632867813110352, "identity": 0.6205980777740479, "hypothesis": "Ik heb het in een kleine dozen gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/086afe8442294266a6913ad49e82d58c406363ee9d56effcc7890dae5c87518a.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "0887566a3a524c67900ac54219de343e4e4c40d97696a838cc1ba01efbcd1879", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18c0e2a0cff28c73fbd08e55f36dd19cee9183f7a1b7faa28c5b06f56cc087d2", "generation_seconds_batch": 20.81924850004725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1066005229949951, "target_z": 1.52343756285806, "ce": 6.0146708488464355, "genuineness": 4.3127899169921875, "identity": 0.4783448278903961, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0887566a3a524c67900ac54219de343e4e4c40d97696a838cc1ba01efbcd1879.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "08c1f6a94b2de6edb32d8462fe6ae611ce221fa83845c8eb797db78c983fa34e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09a1c8eccb3f212a13bd5590ebf3619104fa9ef2d5621eb89460080201763213", "generation_seconds_batch": 19.08834764396306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.499521255493164, "target_z": 2.249999972445782, "ce": 6.078212261199951, "genuineness": 4.632867813110352, "identity": 0.7821661233901978, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/08c1f6a94b2de6edb32d8462fe6ae611ce221fa83845c8eb797db78c983fa34e.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "09b49e9ea7527d04b74d6df6fa6e01ddbd9eea350582c30fa68b60bc80cc8f72", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da10b1a1bcfebcc006d5883dbddd95d9083668519ba2bac887c187be5cd3228e", "generation_seconds_batch": 22.13861166697461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3558728694915771, "target_z": 1.9843751050504568, "ce": 5.605623245239258, "genuineness": 4.005263805389404, "identity": 0.5465701222419739, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/09b49e9ea7527d04b74d6df6fa6e01ddbd9eea350582c30fa68b60bc80cc8f72.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "09cfc20b02e39f748464fce8ee3c7f85fb6c21a274d318fa85fa9d1306a1a248", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57beaa2f99ee0167c407385c0961b7c8355a06112d5bed252e60a730a481eefb", "generation_seconds_batch": 16.67276754695922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767007827758789, "target_z": 4.593750306540677, "ce": 5.561938762664795, "genuineness": 4.595211505889893, "identity": 0.7942516207695007, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade dann. Neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/09cfc20b02e39f748464fce8ee3c7f85fb6c21a274d318fa85fa9d1306a1a248.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "0a15074192591ba54b115d0e13baf6570ea1b707b5127d27d51c7aad18328da1", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75557091575f3e0306e949634e66a72b3db7a3f3388db0a4538fa760b64f4a36", "generation_seconds_batch": 16.347493135021068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.445911169052124, "target_z": 4.000000110216873, "ce": 5.661221981048584, "genuineness": 4.65797233581543, "identity": 0.5868552923202515, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0a15074192591ba54b115d0e13baf6570ea1b707b5127d27d51c7aad18328da1.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "0a189e10bcda5c3c85d54e160559dc48842abb55e6a1347985aeef72ee187d61", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be4013432aa6b71fd33713fa79c1f756e91ea8226be8863f3e58bc211f71d801", "generation_seconds_batch": 20.445837998995557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.054304599761963, "target_z": 5.125000041331327, "ce": 5.998785495758057, "genuineness": 4.68307638168335, "identity": 0.8137571215629578, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0a189e10bcda5c3c85d54e160559dc48842abb55e6a1347985aeef72ee187d61.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "0a25c444ab7e6dc267b3d1d0b76bbdec4ce578f9d137719aa3f9815b39cbc33e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "286a95a27c7c370e2cacd8936cbbee801bac114d2975c62f9e6ed6c73dbe1e5e", "generation_seconds_batch": 16.518020329996943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1501643657684326, "target_z": 3.4531251498260613, "ce": 5.998785495758057, "genuineness": 4.7458367347717285, "identity": 0.7213051319122314, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0a25c444ab7e6dc267b3d1d0b76bbdec4ce578f9d137719aa3f9815b39cbc33e.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "0a365464eda33d4e036ffde1d367dc2de40173019b98abc0d47670bd387ca504", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f18652ebb96b81ce70264d93fa50dce9c2e01cac4f4cb895a148c608ef6ea7a1", "generation_seconds_batch": 20.304166220943443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4728572964668274, "target_z": 0.35156250602748523, "ce": 5.839932441711426, "genuineness": 4.243753433227539, "identity": 0.6043536067008972, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0a365464eda33d4e036ffde1d367dc2de40173019b98abc0d47670bd387ca504.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "0a6858e582f7ba2681436163547ed2419ef004563a6aa806bc1cafdaa414479b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "824861f37e4360ead5f33a421236df1c1065b1815c726cd07cdd7c60b02e5bab", "generation_seconds_batch": 26.590537630021572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.192425936460495, "target_z": -0.1669921738305246, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.42553627490997314, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0a6858e582f7ba2681436163547ed2419ef004563a6aa806bc1cafdaa414479b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "0a9f37017b2b10e471d6cab03d5940c7d57793ddbda427e1e10240a86df3e5ef", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0131da90f18d024bf4ada051628639aee7bd3e959643a0877da1270661456095", "generation_seconds_batch": 15.234916668967344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.817707061767578, "target_z": 4.687499896671682, "ce": 5.855817794799805, "genuineness": 4.984326362609863, "identity": 0.5745903253555298, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0a9f37017b2b10e471d6cab03d5940c7d57793ddbda427e1e10240a86df3e5ef.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "0b07e74f0c50f53127aad6614a6baf3ad5918a60dd59661952c4a30997fcf7c5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75ea65734464c64fa2641f6b476e5daadb5bdeebc4c92a7a8ebbeef5ce89e5fa", "generation_seconds_batch": 20.22344934300054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.014965772628784, "target_z": 3.203125067163407, "ce": 5.174733638763428, "genuineness": 4.457139015197754, "identity": 0.5396983623504639, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0b07e74f0c50f53127aad6614a6baf3ad5918a60dd59661952c4a30997fcf7c5.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "0b0a77c7f9bdb63373fb064a41c52fc0a94d420027fcedb14c40fb9663bcade2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0170559b481fa8b3694107bfdccd36f91bb7e851d48d95b1bd0f3a481e9bed2", "generation_seconds_batch": 14.005090284044854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.081250786781311, "target_z": 1.4765625473588124, "ce": 6.086154937744141, "genuineness": 4.846253395080566, "identity": 0.7449418306350708, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0b0a77c7f9bdb63373fb064a41c52fc0a94d420027fcedb14c40fb9663bcade2.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "0b0cb8ba1ab555f6966e6f1db0da0bf12a2bafba0989a602d2edae8280a114a9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e72a77a110cdbfd1926a36c51488c52182b127e0f4812316458ef4b745eb3679", "generation_seconds_batch": 22.838526348932646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4374613761901855, "target_z": 3.984375325484202, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.6276516914367676, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0b0cb8ba1ab555f6966e6f1db0da0bf12a2bafba0989a602d2edae8280a114a9.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "0bb8aec51bdb293b75a4f8d5702698cef53ea979f3539e6f211fb794f4da9837", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f0973d86a3c789f74cb986865194988fc340cbd6fb6e4133e90d7acc630eed3", "generation_seconds_batch": 19.67727264703717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9360058307647705, "target_z": 4.906249969001505, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.46725213527679443, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0bb8aec51bdb293b75a4f8d5702698cef53ea979f3539e6f211fb794f4da9837.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "0bcc2dace15126b4ed095a56e3300ad51e7bf57b4c173faecbb5bb6946954335", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "346c60eb58630b6006870f45cc4d848ecd4a60d7d68d5750efba9f3124ca8727", "generation_seconds_batch": 23.26229542598594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7192189693450928, "target_z": 2.656250106772595, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.6701197624206543, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0bcc2dace15126b4ed095a56e3300ad51e7bf57b4c173faecbb5bb6946954335.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "0bd023de966545b40ed33f0d46a339f82bf1e20959d2052fea958e2749101047", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e236d5897cbeb62b87457a78d4c4a35c6df6f686be31a6f01086c3b99ca30366", "generation_seconds_batch": 16.53976989304647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22358496487140656, "target_z": -0.10937500861069317, "ce": 6.372091293334961, "genuineness": 4.444586753845215, "identity": 0.4716264009475708, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0bd023de966545b40ed33f0d46a339f82bf1e20959d2052fea958e2749101047.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "0caf94ec9aac4d682e2fbc10312520c63a10d3652e6fe85436526a539dd3a35a", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02c9e811d33637efcefb58ffd19c8659d99fcc65ba8bc6084c766d6ecc77eed5", "generation_seconds_batch": 16.631054269033484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9191060066223145, "target_z": 4.874999958668673, "ce": 6.054384231567383, "genuineness": 4.519899368286133, "identity": 0.5434598922729492, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0caf94ec9aac4d682e2fbc10312520c63a10d3652e6fe85436526a539dd3a35a.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "034ca827f27c02f75513ca0e6f94d244d0288739ca6a7abd6f1c0c42b7bbad37", "generation_seconds_batch": 15.969395963009447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10317376255989075, "target_z": -0.33203124956946534, "ce": 5.95112943649292, "genuineness": 4.3881025314331055, "identity": 0.6627932190895081, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "0cd20812f0f3c3f6c11cad1f5c67cb7a3b73f1bbd717d96d30bf34663d617fac", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6501124bb4a9a0f827234322db243cf14dc2eb5c8be9a7a075e1d2bfc9d5532e", "generation_seconds_batch": 21.471545755979605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8615531325340271, "target_z": 1.0703125232488715, "ce": 5.935244083404541, "genuineness": 4.632867813110352, "identity": 0.6078850030899048, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0cd20812f0f3c3f6c11cad1f5c67cb7a3b73f1bbd717d96d30bf34663d617fac.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "0d9587b030d548b0b50a59d319dbfeac71188de9970db37fc122af79ed70ae8b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9de4064d9384f043672fb82ebed79b1ce37be04a730f792b87d8fedfbf767cad", "generation_seconds_batch": 23.88617042498663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4065723419189453, "target_z": 2.078125136048952, "ce": 5.133034706115723, "genuineness": 4.369274139404297, "identity": 0.7802491188049316, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0d9587b030d548b0b50a59d319dbfeac71188de9970db37fc122af79ed70ae8b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "0e16c81ce660464b48fc31717f84abd1ff6e22b2311f3a4b7ca69d449404b446", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d5719b36f192b5d4ad6638fb91fa65902b11c302163f19faa9f3fb6deff8de74", "generation_seconds_batch": 22.779486375977285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.40920090675354, "target_z": 5.781250258320795, "ce": 5.121120452880859, "genuineness": 4.344170093536377, "identity": 0.3474341034889221, "hypothesis": "J'ai trouvé la petite boîte, elle était boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle comptait.", "wer": 0.21052631578947367, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0e16c81ce660464b48fc31717f84abd1ff6e22b2311f3a4b7ca69d449404b446.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "0ef1d2c708fbb875c6ae549b8a35ce71d4abe84270585e532d66d2b4f14d0a2a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4d2f4620fc12017b7acc950a9f75f4ac380a87f0a8ab2f2fad0cfccb9704d59", "generation_seconds_batch": 19.589108846965246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 6.09409761428833, "genuineness": 4.896461486816406, "identity": 0.8094459772109985, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0ef1d2c708fbb875c6ae549b8a35ce71d4abe84270585e532d66d2b4f14d0a2a.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "0f4046ea8e1aedfea3daef880476b4f2c879df6c5f30b109197ddf97401a7cf2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "74483bd28c24e368628ed7f3fe0ef7fdb2a4dee93d2394d5e65a84c27cc55015", "generation_seconds_batch": 22.6137688489398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9896159172058105, "target_z": 3.1562498312304137, "ce": 5.287916660308838, "genuineness": 4.632867813110352, "identity": 0.6689610481262207, "hypothesis": "Les cuissons sur la table de la cuisine. J'ai regardé dans le tiroir. Puis près de la fenêtre.", "wer": 0.2916666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0f4046ea8e1aedfea3daef880476b4f2c879df6c5f30b109197ddf97401a7cf2.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "0f463dffd8f64610d4d9a2f6f1fd825eca958c1a84756bc75f9277ffeaa17638", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61b565d8606a255f14517271cda9b4be0dcad35eda16f3be8c44bb1efdf9f12a", "generation_seconds_batch": 21.341193660977297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6376305222511292, "target_z": 0.6562499965557227, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.6157181262969971, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0f463dffd8f64610d4d9a2f6f1fd825eca958c1a84756bc75f9277ffeaa17638.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "0f7229fc282e52d165ca61381fabc31ac061b2090beb72678fa7b72baa34ddd2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f3e91362c4b7c816d0a6b670cdef6764556c7d4e08473531ca7947b1d60ea76", "generation_seconds_batch": 15.880102566094138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487090587615967, "target_z": 4.375000234210854, "ce": 5.2918877601623535, "genuineness": 4.469690799713135, "identity": 0.5720223188400269, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0f7229fc282e52d165ca61381fabc31ac061b2090beb72678fa7b72baa34ddd2.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "0fdc25b40f2b00a50af88fdf941f8c3fdb89ae970f0810968b4d1c92d0e4fc7c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7651d1fac39824fe710ad067fe59289a92e8e147318b1f3eccb796fb66367965", "generation_seconds_batch": 19.801386415027082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5980095863342285, "target_z": 4.281250203212359, "ce": 5.728734970092773, "genuineness": 4.758388519287109, "identity": 0.7533819079399109, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/0fdc25b40f2b00a50af88fdf941f8c3fdb89ae970f0810968b4d1c92d0e4fc7c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "101d7f0c683c43d302e2a71a771c56b60fa88274d02e14d7f9ba0bc0b62e1d44", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78e7d3c692fbde2f8de2722899cf6449f9bc86c26ffd7463440eff7414074384", "generation_seconds_batch": 21.04456470499281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5980095863342285, "target_z": 4.281250203212359, "ce": 5.3792572021484375, "genuineness": 4.582659721374512, "identity": 0.5514319539070129, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/101d7f0c683c43d302e2a71a771c56b60fa88274d02e14d7f9ba0bc0b62e1d44.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "10960db2c214efce65e0ff3fd4d44e5c05b2de361fe4c628026e29d5955c891f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7767ee8c4fe30cfe37dabcb4e55b49e4b3617ed2beb3e9b69e513a82ae71991", "generation_seconds_batch": 16.669247722951695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 5.391171455383301, "genuineness": 4.532451152801514, "identity": 0.7152042984962463, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/10960db2c214efce65e0ff3fd4d44e5c05b2de361fe4c628026e29d5955c891f.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "10ad096f3194016f60483fc23a891dc890fb679a7c992db5f07606c4f1ba33ac", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22106fbd8610ee11b84ca5303c470993a00848235ef5bdd33324c4b04b32c041", "generation_seconds_batch": 20.109722063993104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1839640140533447, "target_z": 3.5156251704917247, "ce": 5.685050010681152, "genuineness": 4.7458367347717285, "identity": 0.6494753956794739, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/10ad096f3194016f60483fc23a891dc890fb679a7c992db5f07606c4f1ba33ac.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "10b828239b58857d1f64919130e033c801cd04f87d3afe7fe282a4fcfef6e2e4", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2cb3b2420e2e1590950d1f1fdb4b666118e03bd9609be76b9ba1e51f7a6f4789", "generation_seconds_batch": 21.35679309500847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9022061824798584, "target_z": 4.843749948335841, "ce": 5.728734970092773, "genuineness": 4.193545341491699, "identity": 0.22808045148849487, "hypothesis": "De sleutels liggen op de keukentafel. Kijk in de la. En daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/10b828239b58857d1f64919130e033c801cd04f87d3afe7fe282a4fcfef6e2e4.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "11517d08051fa85c01f87e54cde96b8e0962071385e2fe400a475bf595a54949", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b65963ac235988582f3ca560b8ed6ed34f814bc73b79de0482fe8b0e1c49e04", "generation_seconds_batch": 16.220233965897933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.395211696624756, "target_z": 3.906250079218377, "ce": 5.855817794799805, "genuineness": 4.833701133728027, "identity": 0.8426251411437988, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/11517d08051fa85c01f87e54cde96b8e0962071385e2fe400a475bf595a54949.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "115c93d129f45c85425c5b8c66cf5d43bc15ca5530267aa063d714fcd0886ec6", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45d2f75756474bc9a16689b42d1a54f8aae1db09496590694420fdf9d9f20bc0", "generation_seconds_batch": 16.37485761300195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.395211696624756, "target_z": 3.906250079218377, "ce": 5.696964263916016, "genuineness": 4.758388519287109, "identity": 0.6516692042350769, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu. Puis j'ai arrangé mon téléphone. Dis-moi qu'on nous pourrons parler.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/115c93d129f45c85425c5b8c66cf5d43bc15ca5530267aa063d714fcd0886ec6.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "11a36fbb00ac4f7563d5b9a67b789305f65ad76dd80ae5bc93cb2493e4cde0f5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9b7016b94ee24f18dafd64a002d81bd67b006d0e803206ad262037c166811bf9", "generation_seconds_batch": 16.501798779005185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5304102897644043, "target_z": 4.156250161881031, "ce": 5.998785495758057, "genuineness": 4.118232727050781, "identity": 0.31629133224487305, "hypothesis": "Ik schreef het de nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/11a36fbb00ac4f7563d5b9a67b789305f65ad76dd80ae5bc93cb2493e4cde0f5.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "11bb8afe12e4100341bd7a53a0894877971c2853642fb54575d9b8ccf159b92a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c1a7ab2b58d40634df14f9bca495e19b222d228ebb7ed2e724c1ba613f27aa1", "generation_seconds_batch": 22.185893254936673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.445911169052124, "target_z": 4.000000110216873, "ce": 6.006728172302246, "genuineness": 4.770940780639648, "identity": 0.5881069898605347, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/11bb8afe12e4100341bd7a53a0894877971c2853642fb54575d9b8ccf159b92a.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "124f3831bda40bbb9d107d5351de8cd0d16d50dd51c9444851a671f46c46cdb8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dcef6ca93ae60c236ad8ea277372595949daec936032f98b414b945f0a4bc6e0", "generation_seconds_batch": 15.866516322013922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.375401258468628, "target_z": 5.718750237655132, "ce": 5.6413655281066895, "genuineness": 4.507347106933594, "identity": 0.5729604959487915, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/124f3831bda40bbb9d107d5351de8cd0d16d50dd51c9444851a671f46c46cdb8.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "128a526d5c85a384abbf856a9d0c859e0c008ce98812d81150883b3fce879d76", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2ca5598526556ece83c6b988ccc1945f6f21cff3ebc06ff6ccb0b27056caee9", "generation_seconds_batch": 16.950407529016957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.158614158630371, "target_z": 3.468749934558732, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.42925193905830383, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/128a526d5c85a384abbf856a9d0c859e0c008ce98812d81150883b3fce879d76.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcdcc5890b677a771befa35cbd65efb13a9ff57f8942c3fc5df2e2701890b51c", "generation_seconds_batch": 15.680147695937194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13274843990802765, "target_z": -0.2773437590412278, "ce": 6.197352409362793, "genuineness": 4.457139015197754, "identity": 0.7168571949005127, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "130aa2a57708061421955e2d3dd8754a4521244fc33785481b054919b5484046", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c95e9a946bb15bae268c08ca7f3719e5da03abefcfa65a67c6ff8f8889f0f6ae", "generation_seconds_batch": 21.338193672941998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5443992614746094, "target_z": 6.031249900115959, "ce": 5.140976905822754, "genuineness": 4.394378662109375, "identity": 0.5734735727310181, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/130aa2a57708061421955e2d3dd8754a4521244fc33785481b054919b5484046.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "132b65160e2055ecb1bf9e4d5933825f9d0e1fae3e6f1ae8536b9322dd905b87", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e855d3a9665a7a848ad1ff85b3d5f43efa304d7afbedac8137c08914d12fcc0", "generation_seconds_batch": 14.676003309083171, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6685194969177246, "target_z": 2.5625000757741, "ce": 6.348263263702393, "genuineness": 4.482243061065674, "identity": 0.2723683714866638, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/132b65160e2055ecb1bf9e4d5933825f9d0e1fae3e6f1ae8536b9322dd905b87.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "13ce9c5dfe662075775e84b8b3b5bfd524f0225258cccbd83a4dee7afaee176c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c4e5e0719b6e08550eb1d68cd13e9b35bec5d6472871a8d630ede1bc9fc02059", "generation_seconds_batch": 19.919784166966565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5274996757507324, "target_z": 6.000000330650618, "ce": 5.2045183181762695, "genuineness": 4.444586753845215, "identity": 0.6292850971221924, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/13ce9c5dfe662075775e84b8b3b5bfd524f0225258cccbd83a4dee7afaee176c.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "1535c1ced2a9a4d1ab26e4bb9068e60e341566e9ae09654df09d7203866f320d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09bc708845c9dc2e46a88e7fc72a87b34714df86e0c4a4b918ce4404d8fefb7e", "generation_seconds_batch": 22.757690811995417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2909021377563477, "target_z": 5.562500185990973, "ce": 5.343515396118164, "genuineness": 4.570107460021973, "identity": 0.669690728187561, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1535c1ced2a9a4d1ab26e4bb9068e60e341566e9ae09654df09d7203866f320d.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d048ce0713b7cd3c90becd0095601f2d1a7e6c00a5f35e517479ffd0efd0a5dc", "generation_seconds_batch": 15.790036327089183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8108536601066589, "target_z": 0.9765624922503762, "ce": 6.300607204437256, "genuineness": 4.570107460021973, "identity": 0.6265161037445068, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "15a8f2aac238f11674672f0ab30151773d9c77c9ce0e10ad75c769cf1f0a0223", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "524ee0e943f1bcfbf69ac62684add330ffe20dbac25cd4178df04663393e8c2a", "generation_seconds_batch": 16.566924044047482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9207024574279785, "target_z": 1.1796874491969103, "ce": 5.95112943649292, "genuineness": 4.68307638168335, "identity": 0.6903636455535889, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/15a8f2aac238f11674672f0ab30151773d9c77c9ce0e10ad75c769cf1f0a0223.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "163234d716353d3f25bc63a33b622c5b827316fac7e8822046f50853d40d38c7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba5f5408a57073c74e3d102ac8134b6fb6d4cb204402f5a0b224aa662b9a28af", "generation_seconds_batch": 20.782313095056452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8657780885696411, "target_z": 1.0781250258320796, "ce": 5.796247482299805, "genuineness": 4.319066047668457, "identity": 0.4343827962875366, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/163234d716353d3f25bc63a33b622c5b827316fac7e8822046f50853d40d38c7.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "1656a9b07a338ad2d63928be16fd6920a6de31538d9106b804f0943ec092ad67", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "beb0c6e42f56074fa24e1f977a6afafa6990e00f8198df3d913a8f6ea4884f03", "generation_seconds_batch": 22.13887829007581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07782404124736786, "target_z": -0.37890623751449487, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.6880051493644714, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1656a9b07a338ad2d63928be16fd6920a6de31538d9106b804f0943ec092ad67.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "16c02be77b4bcc315537dbf4dabfd338066a153389c4fd58ff02d3f10291a463", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e90fcfaec6aa22c128543ddadbbb8787b1abaceb777eb08f284072905be1caf", "generation_seconds_batch": 21.608542587957345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9867053031921387, "target_z": 5.0, "ce": 5.895530700683594, "genuineness": 4.6203155517578125, "identity": 0.45328670740127563, "hypothesis": "la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/16c02be77b4bcc315537dbf4dabfd338066a153389c4fd58ff02d3f10291a463.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "1733cb54a68f7b245b39c0b7dac97f5c11f6117cd4f8ef6d269721dbb7478205", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfed2648b863517ab30ee7d250119ec1c99e2f8a89709b9b852c9287c2649b88", "generation_seconds_batch": 20.90114910400007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4910714626312256, "target_z": 2.2343751877131113, "ce": 6.006728172302246, "genuineness": 4.7834930419921875, "identity": 0.771239161491394, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1733cb54a68f7b245b39c0b7dac97f5c11f6117cd4f8ef6d269721dbb7478205.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "177f7a66a0072faa98cf3bb3b6b1590d9a73a7c9f9faca87d1f2a10da157b5d8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9444d0c6aea1568d859d79d67cbbbcb0877c05fca98e558ddcebac2ffe2181b3", "generation_seconds_batch": 16.705174929113127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3445122241973877, "target_z": 3.812500048219882, "ce": 5.3792572021484375, "genuineness": 4.632867813110352, "identity": 0.7546830177307129, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/177f7a66a0072faa98cf3bb3b6b1590d9a73a7c9f9faca87d1f2a10da157b5d8.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "17ccc50279d721fdcc4e206fb05e9732c03cc8edeceb99903cb896d72e3f4b52", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12f4017c5ac860e3d612b5da844b2a6cd4e789806d5881bfcad79958e9ff6757", "generation_seconds_batch": 21.45116779091768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1192753314971924, "target_z": 1.5468749603908114, "ce": 6.173524379730225, "genuineness": 4.8588056564331055, "identity": 0.8341450691223145, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/17ccc50279d721fdcc4e206fb05e9732c03cc8edeceb99903cb896d72e3f4b52.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "18a4c1dcae2dca51ec70bbc5be33fd4597cdaef197f392dcb2c9e9f0f5e9fefa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f839178d81e53bf99da5fb954019d87fcb3229d1bb2cf0e7ca6f0c0f671081b2", "generation_seconds_batch": 16.575806188047864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3445122241973877, "target_z": 3.812500048219882, "ce": 5.1052350997924805, "genuineness": 4.369274139404297, "identity": 0.7014950513839722, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/18a4c1dcae2dca51ec70bbc5be33fd4597cdaef197f392dcb2c9e9f0f5e9fefa.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "18b68e173b86e018ee88a47fd980e4d34583a5138d22a111813a7504d3002df3", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adbd7008b4de8a717f4f34f82612795d3ab47ea5f074fd74e7b8a6fededd6490", "generation_seconds_batch": 15.604210445890203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3896725177764893, "target_z": 2.04687512571612, "ce": 6.006728172302246, "genuineness": 4.582659721374512, "identity": 0.7574558854103088, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/18b68e173b86e018ee88a47fd980e4d34583a5138d22a111813a7504d3002df3.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "18d421ad4ad005491c82aaca6a2d0bdf8cec70af76f91ef98bf1244e5fd423dd", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cb46e3763c89b9b2594d7403ab325fda7ee14243e295b07d24716b0e12e14246", "generation_seconds_batch": 16.075832737027667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.412111520767212, "target_z": 3.937500089551209, "ce": 5.470598220825195, "genuineness": 4.846253395080566, "identity": 0.7272080183029175, "hypothesis": "Les clés sont sur la table de la cuisine, j'ai regardé dans le tiroir, puis près de la fenêtre, prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/18d421ad4ad005491c82aaca6a2d0bdf8cec70af76f91ef98bf1244e5fd423dd.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "18f790ee78d55d10cea36d60c23a37afe260e4b5e697d192f48a00dce5e97ba2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ce76eb5d2457a99d3b0195aac5b01d9766ca07df17589cba8ab617480dd77e1", "generation_seconds_batch": 15.4280356799718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0036051273345947, "target_z": 5.0312500103328315, "ce": 5.704906940460205, "genuineness": 4.645420074462891, "identity": 0.6978654861450195, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/18f790ee78d55d10cea36d60c23a37afe260e4b5e697d192f48a00dce5e97ba2.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "192828e3197ff738b5db4d14a0eb286724f40e72bb17408cdbf71d597adb0807", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62351549da08bdbd8dfddaf9738e1e03bec80cea9ede1fb68e91e126351f447a", "generation_seconds_batch": 15.605766949942335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.267148733139038, "target_z": 1.820312440586217, "ce": 5.903473377227783, "genuineness": 4.093128204345703, "identity": 0.3367610573768616, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/192828e3197ff738b5db4d14a0eb286724f40e72bb17408cdbf71d597adb0807.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "195522191d6bb266e7e4e058533d028f942b62807daf9e1a074573bc35d5d5b4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dc22c46136a0623e578ffef7a7dab7dfa18da756a2b1d47746386154c5e6434", "generation_seconds_batch": 21.40406523901038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5840203762054443, "target_z": 2.4062500241099407, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.5864677429199219, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/195522191d6bb266e7e4e058533d028f942b62807daf9e1a074573bc35d5d5b4.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "1990730ee407bb9dc1e66bbd98dd68e4db1585f64065f1014ae29a0b5d368d75", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "523d47cd4786441b7986ffc3d976a46cfbcbd4ac2085daee95cfcd89ff5dd66c", "generation_seconds_batch": 22.03688767598942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3812224864959717, "target_z": 2.031249900115959, "ce": 5.7128496170043945, "genuineness": 4.494794845581055, "identity": 0.7825855016708374, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1990730ee407bb9dc1e66bbd98dd68e4db1585f64065f1014ae29a0b5d368d75.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "1a0cb7b8e0c23b70775fa45faf1f4ba39f6ec5d5148f8b5747e403b0e7eca480", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94847427cacd9ab469ef56e201fda859c26ece048cdbf5dc83f217c63ee1ff21", "generation_seconds_batch": 22.03688767598942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1953245401382446, "target_z": 1.6875000068885546, "ce": 5.808161735534668, "genuineness": 4.68307638168335, "identity": 0.6335347890853882, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1a0cb7b8e0c23b70775fa45faf1f4ba39f6ec5d5148f8b5747e403b0e7eca480.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "1a1520f27044150cdbd24682d2a9242507affd46b4f743b9fb21c228d434a704", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7f1ea67723bab51479e24648d6c764fd32f2d8f5e206d0dd66ff959f9f9ab088", "generation_seconds_batch": 15.374547465937212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2402026653289795, "target_z": 5.4687501549924775, "ce": 5.696964263916016, "genuineness": 4.7332844734191895, "identity": 0.806944727897644, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1a1520f27044150cdbd24682d2a9242507affd46b4f743b9fb21c228d434a704.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "1a2e22b924762f917d438ad2797eaddf6f731f0541f0c27faeb48ece94c118fd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b823f45026829a614c391dd6a1f11d1a899ba2cb68c52698a52bcc3007de087", "generation_seconds_batch": 21.27539683005307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4242703318595886, "target_z": 0.2617187814290301, "ce": 6.022613525390625, "genuineness": 4.7458367347717285, "identity": 0.6702569723129272, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1a2e22b924762f917d438ad2797eaddf6f731f0541f0c27faeb48ece94c118fd.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "1a398eb0738e2973a58ee3353443e32df2ab64d28b29695646ff56f48b46d475", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9317d13ae7eb32dd65948f44b055db91423ec9c6f1714d6f42f96e199fbafe15", "generation_seconds_batch": 21.44605724106077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.175513982772827, "target_z": 3.4999999448915635, "ce": 5.788304805755615, "genuineness": 4.507347106933594, "identity": 0.6559229493141174, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1a398eb0738e2973a58ee3353443e32df2ab64d28b29695646ff56f48b46d475.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "1a4ebd3efd340f04070ff22cfd9d9e3ed769e41bb9a93c4c71cd308b92447674", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ceb87b6e012e698b2e90b8f32d4c46196c15d75e2f1d9e86fbef55ed03fe1afd", "generation_seconds_batch": 20.29275029199198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5840203762054443, "target_z": 2.4062500241099407, "ce": 5.685050010681152, "genuineness": 4.570107460021973, "identity": 0.7049732804298401, "hypothesis": "Quand quelqu'un a déplacé la petite chaise bleue, elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1a4ebd3efd340f04070ff22cfd9d9e3ed769e41bb9a93c4c71cd308b92447674.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "1bca44114b5b0df64bc67e2d16ca49a9a31c01cd6ede449c7870b74e73374f33", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "493cb0a5d008cba1a5596fe7fa50b2f3fd5fcf5b1726eec1989d05ae57458515", "generation_seconds_batch": 19.646250017918646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5586705207824707, "target_z": 2.359374788176948, "ce": 5.855817794799805, "genuineness": 4.6705241203308105, "identity": 0.7024078369140625, "hypothesis": "J'ai trouvé la petite boîte, elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1bca44114b5b0df64bc67e2d16ca49a9a31c01cd6ede449c7870b74e73374f33.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "1bde81f6e60e1b59ea4c35b99d1c7a83a0cf4954c583eaafb0a725a5a6d1c327", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b4ed9050c009c2a1be18e794a9130cd4f9607365239e3f8b84d5d0cd2648c5f2", "generation_seconds_batch": 15.707980022998527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2895998954772949, "target_z": 0.012695330474822002, "ce": 6.268836498260498, "genuineness": 4.7834930419921875, "identity": 0.6041790246963501, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1bde81f6e60e1b59ea4c35b99d1c7a83a0cf4954c583eaafb0a725a5a6d1c327.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "1c027299a7e959956cd00e09fa7b31846946ba8a09e9188cabc784c743985e72", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b61bd7e582101ba165d9467426b9f91bff49979b9b18cd592462c3712e2f7867", "generation_seconds_batch": 20.722915444988757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.1926045417785645, "genuineness": 4.833701133728027, "identity": 0.7271919250488281, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1c027299a7e959956cd00e09fa7b31846946ba8a09e9188cabc784c743985e72.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "1c4ef7d11d7a95fa07f14ebbaabb043125f09573f48f244339cd21a1c00fd046", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7032711b715ec68e31f6bbd67e6860aeb7108981ca260f2e231d0b59c2f4737", "generation_seconds_batch": 21.479848352028057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1995494365692139, "target_z": 1.6953123992548897, "ce": 5.911416053771973, "genuineness": 4.796044826507568, "identity": 0.7536104917526245, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1c4ef7d11d7a95fa07f14ebbaabb043125f09573f48f244339cd21a1c00fd046.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "1c7bac715151a260c83ab8ef647a95bdfe6efd2a4d672d4e44217ce60ed3ea9b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c851651e522d2a73af36e4bd0de63e5fe3092d85464d7edd1803bace6982acc", "generation_seconds_batch": 15.476135998032987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1628512442111969, "target_z": -0.22167969191298026, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.37554436922073364, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1c7bac715151a260c83ab8ef647a95bdfe6efd2a4d672d4e44217ce60ed3ea9b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "1cb4e87fdcac870d3730e2f942ffa9ec69692ea55903c006c0909f33905a0d3c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "019d3dea6b2181349d21b0d6e854c70820fe306e671021579e810465ae3d410e", "generation_seconds_batch": 21.02740719600115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6418554782867432, "target_z": 0.6640624991389307, "ce": 5.8875885009765625, "genuineness": 4.7458367347717285, "identity": 0.664689302444458, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1cb4e87fdcac870d3730e2f942ffa9ec69692ea55903c006c0909f33905a0d3c.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "1d34ff2e26caba0cdd4c54d20e2b38ae024a2bc64b85520562655e7b4ed2c8fd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ffacd313093b340eb35c854e3a04e631d028991e51cbc14c535ef21142f56756", "generation_seconds_batch": 20.903771981946193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 6.078212261199951, "genuineness": 4.262581825256348, "identity": 0.7418694496154785, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1d34ff2e26caba0cdd4c54d20e2b38ae024a2bc64b85520562655e7b4ed2c8fd.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1f21b46a988d03862e5b16977650ed1ace3d310aaea7560e77e6588bdfa2286", "generation_seconds_batch": 13.829764790949412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00599980354309082, "target_z": -0.5117187538748119, "ce": 6.23706579208374, "genuineness": 4.15588903427124, "identity": 0.6302735805511475, "hypothesis": "Escribí el número en el sobre. Léelo bien. Y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd6ec248c3670987490b27c9794e6ca04b543531c76c643dda79b1b4b2405a0c", "generation_seconds_batch": 14.329132333979942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6143932342529297, "target_z": 0.6132811772396427, "ce": 6.260893821716309, "genuineness": 4.570107460021973, "identity": 0.568306028842926, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "1d9dff2df2612ed065f9ddb8d3051033958f04fa2d3d58db6770699582da9401", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33958da34a033822c09ea2926e2b8928d7040806822df85692bd342ae777bdc9", "generation_seconds_batch": 18.61721174302511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.733208179473877, "target_z": 4.531250285875013, "ce": 5.182676315307617, "genuineness": 4.6705241203308105, "identity": 0.6202759146690369, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1d9dff2df2612ed065f9ddb8d3051033958f04fa2d3d58db6770699582da9401.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "1dee04cc37c7b707fd8b6cc9f4043a6dfa3a869fe04dd7a43cc9d478699dc22a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6aef8212d02ffbfe0512cd8869e35878c4dde02f809d89ba5a88a0d4c489b77", "generation_seconds_batch": 19.722191301058047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6009202003479004, "target_z": 2.4375000344427726, "ce": 5.831989288330078, "genuineness": 4.482243061065674, "identity": 0.2608560025691986, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1dee04cc37c7b707fd8b6cc9f4043a6dfa3a869fe04dd7a43cc9d478699dc22a.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "1e741788ab8b056032ab840d1e7241b4b9b8a7b5531eafced46e2ba82d4bf5f1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d6af2255753956f4d3911dfc357e85d57e1be603f46de5cc1ae5bd40496e32e", "generation_seconds_batch": 22.377174483030103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3614120483398438, "target_z": 3.843750058552714, "ce": 5.692992687225342, "genuineness": 4.425758361816406, "identity": 0.2369922548532486, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1e741788ab8b056032ab840d1e7241b4b9b8a7b5531eafced46e2ba82d4bf5f1.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5278b31707853e88f12ae9e8710d9c96156e09528ee0d3a397b4feb184d6cff2", "generation_seconds_batch": 13.829764790949412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06620541214942932, "target_z": -0.4003906196183168, "ce": 6.141753673553467, "genuineness": 4.582659721374512, "identity": 0.6501420736312866, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "1ef246615804f2bfaf661d04e8ffaa964d56818ff90013578658046f98d67e98", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "100eabab8d266d3536f73b0a07104757729482983aa6e06a8e4c376cf791c000", "generation_seconds_batch": 15.77122448303271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3614120483398438, "target_z": 3.843750058552714, "ce": 5.283945083618164, "genuineness": 4.545003414154053, "identity": 0.729107141494751, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1ef246615804f2bfaf661d04e8ffaa964d56818ff90013578658046f98d67e98.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "1f98170cfc8b047ce08ea0bcb3f99f08291ba02e5dac00b9e0140ef041bf8af9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3bcbb7214eddedd76f9b19570dcb1aa6f0d8845d04e8879e23108cb07543ddd", "generation_seconds_batch": 22.14439023693558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19717900454998016, "target_z": -0.15820312220152472, "ce": 6.324435234069824, "genuineness": 4.300237655639648, "identity": 0.42484450340270996, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1f98170cfc8b047ce08ea0bcb3f99f08291ba02e5dac00b9e0140ef041bf8af9.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "1ff0b29fc4fb45591b234196dcc01de35087bbe7d9a18b0c26ef069d226822ad", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95fb1bc57961a21015edaf2619fbaa5191d08044201bdaa906ef98dbef9aa2bf", "generation_seconds_batch": 16.87762774399016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3347480297088623, "target_z": 1.9453124819175442, "ce": 5.959072113037109, "genuineness": 4.369274139404297, "identity": 0.4190453588962555, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/1ff0b29fc4fb45591b234196dcc01de35087bbe7d9a18b0c26ef069d226822ad.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "2022e7a843b6b66960fe2c9c41dacb1fcb5fc91289ac961ace4b5560bc99781e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b8add8ceebbdce4a63ee5d241557e68821eaffef31849c9de12de6368f28106", "generation_seconds_batch": 21.734626968041994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3474228382110596, "target_z": 1.9687498794502956, "ce": 5.8875885009765625, "genuineness": 4.570107460021973, "identity": 0.5662822127342224, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2022e7a843b6b66960fe2c9c41dacb1fcb5fc91289ac961ace4b5560bc99781e.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "206a48042ee816f9d5b4a66d4100633ad28a2afc2544b7d5547bacba68b46fa9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "129fb53584005c5fb933bf06048a3109c5d977188a45a2cf04cec6f3be875e89", "generation_seconds_batch": 21.902735983021557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4158204197883606, "target_z": 0.2460937762626142, "ce": 6.149696350097656, "genuineness": 4.557555198669434, "identity": 0.3765064477920532, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/206a48042ee816f9d5b4a66d4100633ad28a2afc2544b7d5547bacba68b46fa9.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "20bff649132331207ecbe9899c43177ce8a9e91bf4fc60cadf5948ca829687e3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df85ec23e753e690373ad72abd0809146b8e68c394678fba0f16a1671a29d12f", "generation_seconds_batch": 22.811970324954018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.733208179473877, "target_z": 4.531250285875013, "ce": 5.538110733032227, "genuineness": 4.68307638168335, "identity": 0.5285952091217041, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/20bff649132331207ecbe9899c43177ce8a9e91bf4fc60cadf5948ca829687e3.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "210b9a951db090492e29a858cdbc7d2716f90c463e4b44e847c4ae148ea301f5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2ec42a05dbf3560b29573eea24fa7a9fe128ded27b0349237665ff1bf05471a", "generation_seconds_batch": 16.0709753370611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966670036315918, "target_z": 2.9843749948335843, "ce": 5.601652145385742, "genuineness": 4.582659721374512, "identity": 0.7464727163314819, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/210b9a951db090492e29a858cdbc7d2716f90c463e4b44e847c4ae148ea301f5.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "210e38d480c704ffb56a40924ce263241439d30913638b5ccc2580712767f526", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "811a1d8d7291d801789456a1a40c8ae9ad1bd2fe2db09ee11ad42f4eb8b77a2d", "generation_seconds_batch": 14.005090284044854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9558162689208984, "target_z": 3.0937498105647503, "ce": 5.696964263916016, "genuineness": 4.720732688903809, "identity": 0.779228150844574, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/210e38d480c704ffb56a40924ce263241439d30913638b5ccc2580712767f526.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "2130ed38a6a356f73313c5006ba99b390b4ab899274c271f997de2471780c1b7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "697444c350483cd04dbe9ffe23052e2d9ba6fc6773e46859f5e79d65d06dc4bb", "generation_seconds_batch": 21.554764194064774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8684065341949463, "target_z": 4.781249927670177, "ce": 5.569881439208984, "genuineness": 4.595211505889893, "identity": 0.6937367916107178, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2130ed38a6a356f73313c5006ba99b390b4ab899274c271f997de2471780c1b7.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "215b8ef095efce59e3d799c501adbd7beb568debfdc79138357a1aee4c3bef11", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d75d1bd4a98d2f3a5cff77695a341a5a2f51586069f367fb45262a002c7f0a2", "generation_seconds_batch": 21.510796525981277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.057579040527344, "genuineness": 4.519899368286133, "identity": 0.6568132042884827, "hypothesis": "j'ai j'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/215b8ef095efce59e3d799c501adbd7beb568debfdc79138357a1aee4c3bef11.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "21e734973bdf37b419e68673392f86522f17be86b114b21636b96c79864b6991", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc5e263607358dd98b928918a7061ec0e85b1130fb587473b096c76ccded3a27", "generation_seconds_batch": 20.310784847009927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0221014022827148, "target_z": 1.3671875111939011, "ce": 6.260893821716309, "genuineness": 4.796044826507568, "identity": 0.6697458624839783, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/21e734973bdf37b419e68673392f86522f17be86b114b21636b96c79864b6991.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "225e758d371dfcbc7a27d352201c6744e99daaa64718f68eb966144595288e70", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93e23d1a9f8073ee2ee86ff89232b7c1588212d6929dafc7233d7cf1b0b851cc", "generation_seconds_batch": 21.87470562395174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07676780223846436, "target_z": -0.3808593631602969, "ce": 6.3641486167907715, "genuineness": 4.369274139404297, "identity": 0.5583756566047668, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/225e758d371dfcbc7a27d352201c6744e99daaa64718f68eb966144595288e70.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "22b4bafe277f3f50c8a4a1fabc898ea405e98b5e2fdcc44cd75d8b7bf5b3916a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "485f30188d485ccbfc35cd100994acda2b550ce5f79944acfe882b117c339c27", "generation_seconds_batch": 21.712247720104642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8992955684661865, "target_z": 6.687500117105428, "ce": 5.319687366485596, "genuineness": 4.469690799713135, "identity": 0.5304995775222778, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/22b4bafe277f3f50c8a4a1fabc898ea405e98b5e2fdcc44cd75d8b7bf5b3916a.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "232b13c719d41fbc66b8bb720429103fcb29cd68ceae587d8fd2275783945889", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c80a3471e3306d13fa7180d3ff17d2d937ce7b1f8f6d52aa1f2946c4a376827", "generation_seconds_batch": 14.883724287967198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0601260662078857, "target_z": 1.4375001446596454, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.2945290207862854, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/232b13c719d41fbc66b8bb720429103fcb29cd68ceae587d8fd2275783945889.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "23b7b6b01238dde27f9f94bf08c1a3f7ce5af513c52927581327817865e93847", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52dca2489ba070420bd6eed64b87b4e2e7aed8226088e0727f80cd633b04d054", "generation_seconds_batch": 18.97717561502941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.360097885131836, "target_z": 1.9921877178505374, "ce": 5.7128496170043945, "genuineness": 4.293961524963379, "identity": 0.6295806765556335, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/23b7b6b01238dde27f9f94bf08c1a3f7ce5af513c52927581327817865e93847.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "244c5f13bfe0298b842f32b176f13233baf05b8b1c56d09d789eb9cf62405134", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78d6bd1eac9036ecfa25e36a279f60c7e731470613af4dbf796affae9c2aeadc", "generation_seconds_batch": 21.45116779091768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5320066213607788, "target_z": 0.4609374319755239, "ce": 5.9431867599487305, "genuineness": 4.595211505889893, "identity": 0.5932419300079346, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/244c5f13bfe0298b842f32b176f13233baf05b8b1c56d09d789eb9cf62405134.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "248a31f59381051725567665c911d14b3a492d5d4227b02ea00162591980e059", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb6ccb3592b508586043beed27c33d6f8b220cdc3dfeddcff4099adea248e900", "generation_seconds_batch": 19.761636762996204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26425015926361084, "target_z": -0.03417968502442571, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.4086143374443054, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/248a31f59381051725567665c911d14b3a492d5d4227b02ea00162591980e059.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "248b64689bf574b1ec851ebfae7e4d5139d94812c867caa2c291e5abfb1b8070", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "19ad427290e87b3a54500b34265a29fc7202bc5cdfa07a1a76b3dc78f6f30e43", "generation_seconds_batch": 16.631054269033484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.919358730316162, "genuineness": 4.6956281661987305, "identity": 0.7014407515525818, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier. Naast de hoge boekenkast. We zetten het na de lus terug.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/248b64689bf574b1ec851ebfae7e4d5139d94812c867caa2c291e5abfb1b8070.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "24924facfb461d0e08ee579a803c3d5608a9506093ac2be089f3f32adcca74b7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b557efaed3e9f2070cc70e954e7d72be6b8192e1b93f7d2a7b9b3b5c639ce62e", "generation_seconds_batch": 16.438179277000017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.478540420532227, "genuineness": 4.582659721374512, "identity": 0.52885502576828, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/24924facfb461d0e08ee579a803c3d5608a9506093ac2be089f3f32adcca74b7.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "25aecfd37c25d93d93f6ff2bf66cb9419c47d64adce48d6b57afb5bcd46bd81a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "76b3a296798ef4e7120faac9f7ec99b51e02dbd643fa92d4dcdc956e6a3321fb", "generation_seconds_batch": 21.338193672941998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 5.442798614501953, "genuineness": 4.482243061065674, "identity": 0.6360474824905396, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/25aecfd37c25d93d93f6ff2bf66cb9419c47d64adce48d6b57afb5bcd46bd81a.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "25ecaea7ef26c37d296fe675baab1c106ac9c340c87c3489d6467cbe0a60f79c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d695fcc39f74c344cd632c77cc854f5cd10b76fc8c5b5b5f2ae7778e072a41d", "generation_seconds_batch": 20.00661881803535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9135668277740479, "target_z": 3.0156250051664157, "ce": 5.585766792297363, "genuineness": 4.770940780639648, "identity": 0.6331015229225159, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/25ecaea7ef26c37d296fe675baab1c106ac9c340c87c3489d6467cbe0a60f79c.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "264b080449ee95c1416411ece729c4223c8c958b9965301adc5b48bf1df349e3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b70db3bf6d2fd7f495b1ae9c0f676ab77ce9364aaedb3fafc3855d09c8633e68", "generation_seconds_batch": 20.49008314392995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.285362958908081, "target_z": 3.703125232488716, "ce": 6.0305562019348145, "genuineness": 4.519899368286133, "identity": 0.2924937903881073, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/264b080449ee95c1416411ece729c4223c8c958b9965301adc5b48bf1df349e3.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "268c8b8d33d77de2c0194295e2c687578bfcbf3ca6c92e8a3a361bbf4471bd11", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53ace07137770de14f765580ad29873e681318f52a3df896508e2255c54de1fd", "generation_seconds_batch": 21.902735983021557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0009765625, "target_z": 1.3281248880609888, "ce": 6.38003396987915, "genuineness": 4.8588056564331055, "identity": 0.28884047269821167, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/268c8b8d33d77de2c0194295e2c687578bfcbf3ca6c92e8a3a361bbf4471bd11.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "26994d685f1e648f518bfdedcab7f19de309f84c70fb1e887f1872cceedcab41", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "658e697a68fd3a26e782f05f5c335eb124978d69a121c009790c6543846d186f", "generation_seconds_batch": 23.511925903032534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6854193210601807, "target_z": 2.593750086106932, "ce": 5.903473377227783, "genuineness": 4.375550270080566, "identity": 0.4485085606575012, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/26994d685f1e648f518bfdedcab7f19de309f84c70fb1e887f1872cceedcab41.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "26b9c63b52af0ec6228842385b815ca0e63066885f296c18310a2d46aad69186", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8aa39e1f329c388fde22cbe94f8c2d8dd5b15be8c2b763f16c020c282a8779ba", "generation_seconds_batch": 20.861773938057013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46281099319458, "target_z": 4.031250120549704, "ce": 5.1052350997924805, "genuineness": 4.507347106933594, "identity": 0.5920721292495728, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/26b9c63b52af0ec6228842385b815ca0e63066885f296c18310a2d46aad69186.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0f1cb7fc36b43971e9fb72d8947518418e3cbb1f81257b51aff8f1f120f61fe", "generation_seconds_batch": 15.012961250031367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09155513346195221, "target_z": -0.3535156316732872, "ce": 6.348263263702393, "genuineness": 4.369274139404297, "identity": 0.22595234215259552, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "270e0923351695a113f0ab4331c270315330d8267df1aa395d71e58d2fa99b5d", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9b772289e2e838acd643e76fd4cfb4468589418320acd54b3343ca8114f5d42", "generation_seconds_batch": 15.673256810056046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3556148111820221, "target_z": 0.134765642006119, "ce": 6.205295085906982, "genuineness": 4.193545341491699, "identity": 0.3678152859210968, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/270e0923351695a113f0ab4331c270315330d8267df1aa395d71e58d2fa99b5d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "273356c6b90bb803b1c6e7a1206944da7100a0b80708a8178a4969dadf3b1434", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "99b91c9048b717fc9605fba152392eb311896aa60396a76e08ddb5348badb726", "generation_seconds_batch": 20.11870645696763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9207024574279785, "target_z": 1.1796874491969103, "ce": 5.426913261413574, "genuineness": 4.118232727050781, "identity": 0.2905411720275879, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/273356c6b90bb803b1c6e7a1206944da7100a0b80708a8178a4969dadf3b1434.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "27b5930d6326d80f90f1073ea681b2186de7618cec604a956e1203f94a0d0209", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3fd58aa71c73ce9613d89b103a322c32bfee2c76327911a6ea282891dbbd2c42", "generation_seconds_batch": 22.14953198703006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2417991161346436, "target_z": 1.7734376455207146, "ce": 5.95112943649292, "genuineness": 4.6705241203308105, "identity": 0.42912763357162476, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/27b5930d6326d80f90f1073ea681b2186de7618cec604a956e1203f94a0d0209.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "27b8ca4808efe12fb3c6d8e2d8c59870f59fce98fbd5eb54287e526714c0d482", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb5557908b8a014510e68791ae36d7ab19d9f43502dce2bec81af743ce9a3dff", "generation_seconds_batch": 15.786097209900618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.716308355331421, "target_z": 4.500000275542182, "ce": 5.681078910827637, "genuineness": 4.7332844734191895, "identity": 0.6655929684638977, "hypothesis": "Me he encontrado la cajita, estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/27b8ca4808efe12fb3c6d8e2d8c59870f59fce98fbd5eb54287e526714c0d482.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "27fa90e7bfffda2074213162cc756cac5d368ba1c0e96848e5334d86843c1576", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6be7e03f81cd527ef00b1706dcd274e645085e08402c7aa229074bdb2161e79c", "generation_seconds_batch": 21.411917366087437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.608055830001831, "target_z": 0.601562478473267, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.4104098975658417, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/27fa90e7bfffda2074213162cc756cac5d368ba1c0e96848e5334d86843c1576.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "2817cfb5b4fe5f9b687b4d20da9dd2ca558191301aa30cca1b72f00dae9202ec", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e5b9f44ffe98c27c02a3215702d91564a6de62e795ad5a3c1ccbd85d2628bf81", "generation_seconds_batch": 20.782313095056452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5135104656219482, "target_z": 4.1250001515482, "ce": 6.022613525390625, "genuineness": 4.796044826507568, "identity": 0.6429387927055359, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2817cfb5b4fe5f9b687b4d20da9dd2ca558191301aa30cca1b72f00dae9202ec.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "28a650f1328cfbbdda7a455c72ca79726e5564a6614b72bc34a319d65cd979f8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b38199209133e7b6c918c961f5e4ab95f6b65bab5656e77b76193f3cf6a43b98", "generation_seconds_batch": 14.862544005038217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3643226623535156, "target_z": 1.9999998897831273, "ce": 5.6254801750183105, "genuineness": 4.419482707977295, "identity": 0.5331820249557495, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/28a650f1328cfbbdda7a455c72ca79726e5564a6614b72bc34a319d65cd979f8.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "28b96d696ec509550acdc94970091d110a25c86873e9bf37c7be29b152a0c648", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "31a7acedb63cc38310487fa576a407edd8b9691454008cc0fa81e84365458abd", "generation_seconds_batch": 20.725076679023914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7023191452026367, "target_z": 2.6250000964397637, "ce": 5.137005805969238, "genuineness": 3.8922953605651855, "identity": 0.39692258834838867, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/28b96d696ec509550acdc94970091d110a25c86873e9bf37c7be29b152a0c648.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "28c08bd6bb185e46912306752e17aa5db08a0a9d68a508b2df86693474a8b37c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c9e30f9a8edfc07f97245554af85e959b6192ff7e9a5ed9087f4c306ee15c8d", "generation_seconds_batch": 20.22344934300054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8853063583374023, "target_z": 4.812499938003009, "ce": 5.597680568695068, "genuineness": 4.6956281661987305, "identity": 0.7470614910125732, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/28c08bd6bb185e46912306752e17aa5db08a0a9d68a508b2df86693474a8b37c.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "28cbdb6d5ec5df5788d6b9fd2c0f5130ee7adb7aee107361374268f32354e84d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "364907d9e92d24adf38d8bf4aa3a445166ef623b1c2ea5c54cfd65e8fa62d44a", "generation_seconds_batch": 22.07898157904856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7192189693450928, "target_z": 2.656250106772595, "ce": 5.49045467376709, "genuineness": 3.9048471450805664, "identity": 0.4813377261161804, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/28cbdb6d5ec5df5788d6b9fd2c0f5130ee7adb7aee107361374268f32354e84d.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "29840a3f7c50ef2131ecafd22866f49af6535132ca7336e07f03760e593ceaa3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea68c088b697ad868c78baf342a98f2dbf82b3f83445df8fe463ea0599e91ccb", "generation_seconds_batch": 17.36983169405721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9161953926086426, "target_z": 6.718750127438259, "ce": 5.383228778839111, "genuineness": 4.519899368286133, "identity": 0.5889503955841064, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/29840a3f7c50ef2131ecafd22866f49af6535132ca7336e07f03760e593ceaa3.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "2a15b40c2b05288bc668682ef1afe693829d401d4446c6b2c28f56b6d47aa826", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3a5899ef3fcab2fb49c1c474bc56b91a98e486dc760dffd0d97805f9ecd1ce8b", "generation_seconds_batch": 16.669247722951695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9360058307647705, "target_z": 4.906249969001505, "ce": 5.696964263916016, "genuineness": 4.770940780639648, "identity": 0.6330955028533936, "hypothesis": "La porte a encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2a15b40c2b05288bc668682ef1afe693829d401d4446c6b2c28f56b6d47aa826.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "2a3be9375b17317cd441b78a633795f0dc9c6d9829b6171f86938dd701c1ab80", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4eacc2d9a621a722f8f681c20eacc0f6f6caa5397d38a2ccb67c785bb4ab533", "generation_seconds_batch": 15.503090420970693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.831978440284729, "target_z": 1.015625005166416, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.6372592449188232, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2a3be9375b17317cd441b78a633795f0dc9c6d9829b6171f86938dd701c1ab80.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "2a67f7cabd51d6702226d5d14a24b8478eb3012c07daea3109dc0181ffa23729", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "256c2cad0068feb409da73fe8e84842dab78a498ab137cedcb9fb3187ec196f0", "generation_seconds_batch": 16.124050904996693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.319162607192993, "target_z": 3.7656252531543792, "ce": 5.33954381942749, "genuineness": 4.632867813110352, "identity": 0.8289638757705688, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis les biens et vérifié les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2a67f7cabd51d6702226d5d14a24b8478eb3012c07daea3109dc0181ffa23729.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "2aa0b76fa9163816d4ccde61a64f11e8636e36e6e04ca9853b39b94e77276b20", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42126ff7d021923eaf2acd34b4165a4224d2939379f7b586405e8e99cb0c049f", "generation_seconds_batch": 21.0510713160038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7361187934875488, "target_z": 2.687500117105427, "ce": 5.522225379943848, "genuineness": 4.519899368286133, "identity": 0.6282027959823608, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2aa0b76fa9163816d4ccde61a64f11e8636e36e6e04ca9853b39b94e77276b20.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "2b8dc9eec2196b96636883703a12735931f56e8c78f183dbc10be4d826c4774f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0fc22082d1aaa4aaa30d7ca3bb32a45a661bdc95b3973e5b9a409a5e88c7cbd", "generation_seconds_batch": 20.25352051097434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35825538635253906, "target_z": 0.13964841478929674, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.5007016658782959, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2b8dc9eec2196b96636883703a12735931f56e8c78f183dbc10be4d826c4774f.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "2b96ff5582e6ed7eab16aa774dd408cc25bc2f4fbe79c43a46fc35e56107bf96", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9181e85cae44ad796c7d2410445a54931dac1168da3b10e3164dcd6fa65c0be8", "generation_seconds_batch": 14.744484603055753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124814510345459, "target_z": 3.406249913893068, "ce": 5.522225379943848, "genuineness": 4.457139015197754, "identity": 0.6751487851142883, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le temps.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2b96ff5582e6ed7eab16aa774dd408cc25bc2f4fbe79c43a46fc35e56107bf96.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "2c63d9a19dcc61e776078ba753c25443877f77e7bd61865f14bc08a5d125d74e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4ad6321bc0648c75b187c2dbe087ee5cb3aad4b080cb8804ba87430c6ee4e583", "generation_seconds_batch": 20.082475688075647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.322073221206665, "target_z": 1.9218750843847932, "ce": 5.015880107879639, "genuineness": 4.105680465698242, "identity": 0.5772377848625183, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2c63d9a19dcc61e776078ba753c25443877f77e7bd61865f14bc08a5d125d74e.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "2c64ec4eb5f7cac25047bb3eb78a731b8320582629632012b77ce12b0783d980", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3393ea32131c15615fcd0b9332076a579821ddd31272ab715e6961f1e8839aab", "generation_seconds_batch": 14.09338602796197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.682508707046509, "target_z": 4.437500254876518, "ce": 5.689021587371826, "genuineness": 4.532451152801514, "identity": 0.4299599528312683, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. It will meet you on the other side.", "wer": 0.041666666666666664, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2c64ec4eb5f7cac25047bb3eb78a731b8320582629632012b77ce12b0783d980.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "2cf0177c031ffe0350b15894ccc75c2387efc258fc9bc34acab19862ffb163c4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73bbf190f5020d4b91aecf89a22f9bf17a87be25782c1fb11256d7dd390d6c46", "generation_seconds_batch": 15.117723227944225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6178200244903564, "target_z": 2.4687500447756046, "ce": 5.998785495758057, "genuineness": 4.7081804275512695, "identity": 0.8105688095092773, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2cf0177c031ffe0350b15894ccc75c2387efc258fc9bc34acab19862ffb163c4.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "2d024bb19bb2617c416b524aa8c581ad89001c6b85542424d72059225cbebb29", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa9e24586cfefabea85b93d2207e0185d905964d0f85c897fb2a123edfe63b13", "generation_seconds_batch": 25.238044171012007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2402026653289795, "target_z": 5.4687501549924775, "ce": 5.6413655281066895, "genuineness": 4.300237655639648, "identity": 0.26568400859832764, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2d024bb19bb2617c416b524aa8c581ad89001c6b85542424d72059225cbebb29.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "2d0cf8bd56419a6da29634f5258336aa66a21e9bc4ee613104987266ab6c1e03", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a55eaa99dd85d18833b16255a72c071ab6b5a358699a5bcf20619d78c42a659d", "generation_seconds_batch": 16.562658303999342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31891050934791565, "target_z": 0.06689453270305447, "ce": 6.054384231567383, "genuineness": 4.469690799713135, "identity": 0.5316619873046875, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2d0cf8bd56419a6da29634f5258336aa66a21e9bc4ee613104987266ab6c1e03.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "2dd19923a6483f9be54ed613257edefc03507a41d8b29fded86c9198386a9674", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71ea4ae5271735303f6478e25cc415f126e62e1a70b32a0ceecabd0a636dde7a", "generation_seconds_batch": 20.91891167103313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767007827758789, "target_z": 4.593750306540677, "ce": 5.6254801750183105, "genuineness": 4.582659721374512, "identity": 0.4644898772239685, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2dd19923a6483f9be54ed613257edefc03507a41d8b29fded86c9198386a9674.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "2ddf4ca3f50a2304f2915deaf0925faaba6ba818e1e58ac0dc398c4d94318492", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c26fa772a92bf0ee506e6530f8fff6d137843c99b056d5af45d5be31766e24b", "generation_seconds_batch": 16.347493135021068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9867053031921387, "target_z": 5.0, "ce": 5.657250881195068, "genuineness": 4.507347106933594, "identity": 0.7212871313095093, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2ddf4ca3f50a2304f2915deaf0925faaba6ba818e1e58ac0dc398c4d94318492.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "2e1b7ba4e7d21769cae5e3502b4238d10d4c4512c9da6b3a2c334b42a79bce6e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e962daa734a3b07be2ca88c589e370ee2d04298fe42a84717751664baea84c9", "generation_seconds_batch": 15.603769718902186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9360058307647705, "target_z": 4.906249969001505, "ce": 5.689021587371826, "genuineness": 4.582659721374512, "identity": 0.822553277015686, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2e1b7ba4e7d21769cae5e3502b4238d10d4c4512c9da6b3a2c334b42a79bce6e.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "2e770e3c18c7ec132926a938dc3c8a85d4e25039b44c32829e502562603b6daa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f152a6c0fec15d974665b38c14b1c2f6a37767bd10ae35f5f9c9ab130a2c82bf", "generation_seconds_batch": 22.50948345893994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.251563310623169, "target_z": 3.640625211823052, "ce": 6.0146708488464355, "genuineness": 4.808597087860107, "identity": 0.6799739599227905, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2e770e3c18c7ec132926a938dc3c8a85d4e25039b44c32829e502562603b6daa.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "2e905d5fd37261aaafbe791feedc6711ac12fb3656289f715c61673e4baf1bdd", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca49adc4e79015977bed152b8baa07585df9eef107dcc6fcf7f870f7f5ada21d", "generation_seconds_batch": 15.225561915896833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.107914686203003, "target_z": 3.3749999035602363, "ce": 4.99999475479126, "genuineness": 4.3881025314331055, "identity": 0.6207275986671448, "hypothesis": "Deine Nachricht kam, als sie schon weg war. Ich las sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2e905d5fd37261aaafbe791feedc6711ac12fb3656289f715c61673e4baf1bdd.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "2e9399a2b4ebed3b54561223592caa987e91fd99df1cdf30cd5802544dfda8a6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93874c7ea5545925548c2a677b1fb892c8d56c95a3b1cae8e9dc26fac7d3f567", "generation_seconds_batch": 22.554253038018942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.72001713514328, "target_z": 0.8085937418198414, "ce": 6.0146708488464355, "genuineness": 4.68307638168335, "identity": 0.747556209564209, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2e9399a2b4ebed3b54561223592caa987e91fd99df1cdf30cd5802544dfda8a6.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "2ef41f3f754afc198eb1a49f982df49d3b63943f3d82b16fcafca3a7900c2ee5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c67c536d6a95a224c823ccc8e755abed921d44642de2e05ddf5f1e1df94ec20a", "generation_seconds_batch": 22.219423627946526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2066851556301117, "target_z": -0.1406249913893068, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.4484812319278717, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2ef41f3f754afc198eb1a49f982df49d3b63943f3d82b16fcafca3a7900c2ee5.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "2f3a84e9bc6d0b71986d38986b8e4f591c29566636d4d84b04fc62a7625c4ba8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a94f49b09fe5266cc3217a1afef2d207f681823563052e075575af32d3b52e9", "generation_seconds_batch": 19.758079020073637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.446769714355469, "genuineness": 4.7332844734191895, "identity": 0.7064995765686035, "hypothesis": "Mais j'ai trouvé la petite boîte elle était près de la vieille fenêtre Nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2f3a84e9bc6d0b71986d38986b8e4f591c29566636d4d84b04fc62a7625c4ba8.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "2ff1d010d301a136f2b1bc149edcad38c3ff70e098655f89bcdafad1e12dd8f5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "111ab1d8dee5ee8cc3a8572ec50a088a30f8ac3505eab485034130c01ebfdda8", "generation_seconds_batch": 21.554619478061795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6347198486328125, "target_z": 2.5000000551084365, "ce": 5.3792572021484375, "genuineness": 4.268857479095459, "identity": 0.4907008707523346, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/2ff1d010d301a136f2b1bc149edcad38c3ff70e098655f89bcdafad1e12dd8f5.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "3001d378782289822ba73a4b92fb5a821ab55d67a9cb0692069b84195ee15755", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2d0cc508c7f6e226200bc3442a72bd10a9ea1f70bff7ce7ce88c28d178813f32", "generation_seconds_batch": 22.71827597497031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9867053031921387, "target_z": 5.0, "ce": 4.942410469055176, "genuineness": 4.519899368286133, "identity": 0.4391101896762848, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3001d378782289822ba73a4b92fb5a821ab55d67a9cb0692069b84195ee15755.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "303d5484081ced6759dc261c96547347c15627d0bff7ed61e8a5ef8d8906a4b5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c47e08826f9f51eeb650ac25ae8eba56cf335568ff974c6a78d067401798e165", "generation_seconds_batch": 21.573268500971608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8615531325340271, "target_z": 1.0703125232488715, "ce": 6.316492557525635, "genuineness": 4.909013748168945, "identity": 0.7448245882987976, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/303d5484081ced6759dc261c96547347c15627d0bff7ed61e8a5ef8d8906a4b5.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "3073e5d46f2467492f899c8efdd7fa9dcfb6ed240a2311e40b67efae5a397a2a", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd1278b954656f6e949146175387d2b2a6ffd0dc64e67e5785b914ba16e8cee3", "generation_seconds_batch": 14.301881296094507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3812224864959717, "target_z": 2.031249900115959, "ce": 5.895530700683594, "genuineness": 4.344170093536377, "identity": 0.48778969049453735, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3073e5d46f2467492f899c8efdd7fa9dcfb6ed240a2311e40b67efae5a397a2a.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "30d04f98ebf09567b91f59927b2f6b9cab5971e9e1860c6daf45d86001e1e1a2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "366db32fff6b7e7443351b8e013987b8d737ff52b72748941966f8ae1df9f0c7", "generation_seconds_batch": 20.966576074948534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5755703449249268, "target_z": 2.3906247985097795, "ce": 5.967014789581299, "genuineness": 4.808597087860107, "identity": 0.7034071683883667, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/30d04f98ebf09567b91f59927b2f6b9cab5971e9e1860c6daf45d86001e1e1a2.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "310ae003a33c0f7f139c08fa73bec81fe8b59b4693b102db38aafe6b788488b7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4101f1598da9e04422852d2fd8a0aba5091a40fb2ffbc30ef6df6268082e357", "generation_seconds_batch": 21.341193660977297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.465721607208252, "target_z": 2.187499951780118, "ce": 6.23706579208374, "genuineness": 4.720732688903809, "identity": 0.6578431129455566, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/310ae003a33c0f7f139c08fa73bec81fe8b59b4693b102db38aafe6b788488b7.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "315004f376cff96c1a7a3acbad7d00be0782da52c0cff4f5cdc7a3a88532c6a4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6163b5d3b4174f64c041addc30815ac3dbd8d5c66a1e56d46eb65d02ab2af5f1", "generation_seconds_batch": 21.539820856996812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.637393951416016, "genuineness": 4.444586753845215, "identity": 0.3271912932395935, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/315004f376cff96c1a7a3acbad7d00be0782da52c0cff4f5cdc7a3a88532c6a4.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "31a45248856a3167c549327a1ddeb831cd367c86684943a1a79cfb10bd5eeedf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1b3d26da38737db728a499f8d7bcc4085d93854dab0ae44438d2aac42588361", "generation_seconds_batch": 21.539163448964246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.338973045349121, "target_z": 1.9531250947176249, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.5867382287979126, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/31a45248856a3167c549327a1ddeb831cd367c86684943a1a79cfb10bd5eeedf.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "321ca63018dedb76b638111f4b1afa8be018c34c895d7f89f9b00d40c01dc50b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "88c42eefd3d33ff55143cebdbb8c7ed9a37043853c68e646a0a4dd1309b567a6", "generation_seconds_batch": 16.075832737027667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.803718090057373, "target_z": 2.8125001584367544, "ce": 5.343515396118164, "genuineness": 4.68307638168335, "identity": 0.5933996438980103, "hypothesis": "Oh les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prenez quand tu partiras.", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/321ca63018dedb76b638111f4b1afa8be018c34c895d7f89f9b00d40c01dc50b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "32d7f61bb2b3feefbb7d7c7970a71f1b4757f1e5aa5230c6048fad292a63dbac", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0963749c0489f26b7a2145650596ed2f5327bddc862d902689411c720088bc6", "generation_seconds_batch": 23.77136810205411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6854193210601807, "target_z": 2.593750086106932, "ce": 5.71682071685791, "genuineness": 4.7332844734191895, "identity": 0.7652859091758728, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/32d7f61bb2b3feefbb7d7c7970a71f1b4757f1e5aa5230c6048fad292a63dbac.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "32e62eb3d4c02c044b32ad888122730a1becdbdc0b3f7a23379a3a66eb3df124", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7169b42928fd246a1e8b87b7b6d17a342202f3cd9afc3969f0664e540e02b4bc", "generation_seconds_batch": 20.34587400802411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.034776210784912, "target_z": 1.3906249087266525, "ce": 6.070269584655762, "genuineness": 4.632867813110352, "identity": 0.7119839191436768, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/32e62eb3d4c02c044b32ad888122730a1becdbdc0b3f7a23379a3a66eb3df124.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "330e82ee7c0d72c5e4087bcb49f5c987b731cf7bc0376d3d4ea8355cbdc7bd66", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb7d6c7010fb50380c38411fa040ed5b328aa11eb836e1294a47e83c45f8719a", "generation_seconds_batch": 22.552604004042223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.582706093788147, "target_z": 0.5546874629740194, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.2781807780265808, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/330e82ee7c0d72c5e4087bcb49f5c987b731cf7bc0376d3d4ea8355cbdc7bd66.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "331db348a9fb39944d4cd338d54f121fe3fb8d87b1cc96c6b67859dd622e4872", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "733f2fe71284f28462bf8524a68cb7b7b39db7d8839c057f63959c91c534fab6", "generation_seconds_batch": 21.02312556304969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.800807476043701, "target_z": 4.65625032720634, "ce": 5.542081832885742, "genuineness": 4.582659721374512, "identity": 0.7530868649482727, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/331db348a9fb39944d4cd338d54f121fe3fb8d87b1cc96c6b67859dd622e4872.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99e5812f169f1a19e41e03a9ede1c6b48b3f3d4daee19a2794f4decd898d39de", "generation_seconds_batch": 15.416113436105661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1163647174835205, "target_z": 3.3906251291603975, "ce": 5.967014789581299, "genuineness": 4.2751336097717285, "identity": 0.619260311126709, "hypothesis": "De weg gaat linksaf na de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "346b97ff665a732784ee5fb2fe3bdbeb528c358e91ba3a5826add39fa8b00b0c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "faa6425c4494f5c7d6df815ba1314cb2595b812d0188d87fd8cdf23f283c1201", "generation_seconds_batch": 25.313960302970372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1446250677108765, "target_z": 1.593749975890059, "ce": 5.8875885009765625, "genuineness": 4.413206577301025, "identity": 0.5347579717636108, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/346b97ff665a732784ee5fb2fe3bdbeb528c358e91ba3a5826add39fa8b00b0c.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7716d7788662975e63306129591615f2c7be92efc37c60d628e7934a5adbc4aa", "generation_seconds_batch": 14.93534094991628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.323927640914917, "target_z": 0.07617187263205938, "ce": 6.4912309646606445, "genuineness": 4.2374773025512695, "identity": 0.44279998540878296, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "34af90ecfe6bb93f75c09482bf051f5232b108319a3d77492f39b01f18bf71ba", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccf16bc108aa3d3a56761830f716f1ff533ae2b740ecbd1a1c4639e39c1a30b0", "generation_seconds_batch": 21.101911879959516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.107914686203003, "target_z": 3.3749999035602363, "ce": 6.109982967376709, "genuineness": 4.883909225463867, "identity": 0.784268856048584, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du weit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/34af90ecfe6bb93f75c09482bf051f5232b108319a3d77492f39b01f18bf71ba.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "351a78c5594e9d6ac29af0f2e4b81ac6426bcd00abbe95c0015fc25fead0e056", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee5c4d6ee9fa913050f8b543f9e5b7ff3d7dbca0af221476f587c5c3b852fef3", "generation_seconds_batch": 21.539163448964246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6318092346191406, "target_z": 4.343750223878023, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.5576798915863037, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/351a78c5594e9d6ac29af0f2e4b81ac6426bcd00abbe95c0015fc25fead0e056.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "353661fd8f20a17c357fbd99d8417fb75d06e6e179ecc13d420a1599b8d221d4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b706c8a40c831f43c86d736d172940736ac599eb8490db490339cd37149b027", "generation_seconds_batch": 20.643091156031005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5108819007873535, "target_z": 0.4218750292763568, "ce": 6.41180419921875, "genuineness": 4.6956281661987305, "identity": 0.7047134041786194, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/353661fd8f20a17c357fbd99d8417fb75d06e6e179ecc13d420a1599b8d221d4.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "35495266359567626c85449aebc0f3881f15b8b19f71787633a1318e0f177c4b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42b1bec68f0bb3bb5dbbbde088a04113471ba92ce36ed081009bcb7a47ffb914", "generation_seconds_batch": 15.250085219042376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2037744522094727, "target_z": 1.7031250120549704, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.6633417010307312, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/35495266359567626c85449aebc0f3881f15b8b19f71787633a1318e0f177c4b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "354e8d6a434453e245e17164b7a04ea111b5ad56cfcc61358d6b41e7eb0e836c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c0f24cf2924554c698a943b144b4ccec677a366135b16b2681f2fd4e866713ae", "generation_seconds_batch": 22.23410872905515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.305173397064209, "target_z": 1.8906250740519612, "ce": 5.927301406860352, "genuineness": 4.545003414154053, "identity": 0.4878132939338684, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/354e8d6a434453e245e17164b7a04ea111b5ad56cfcc61358d6b41e7eb0e836c.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "35e477c885ca040ff35e662ba92832b778d48131521372d8d17d8576528bfb55", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbd479d584aa3b70c2ad26d2ccc021104eee7c45e8432f011d0c1cc11314240b", "generation_seconds_batch": 22.58910707605537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5443992614746094, "target_z": 6.031249900115959, "ce": 5.4666266441345215, "genuineness": 4.557555198669434, "identity": 0.8496229648590088, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/35e477c885ca040ff35e662ba92832b778d48131521372d8d17d8576528bfb55.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "363f127839c7a3df15e7adb1c3da151b70f70ce084b1b1c7b2d9c973805343f9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2d77f5a12b6df7b844d931c48a897614d610abbe29038a0027b6490a401a778", "generation_seconds_batch": 16.80797480500769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.863759994506836, "genuineness": 4.469690799713135, "identity": 0.32816237211227417, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude. Daar gaan. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/363f127839c7a3df15e7adb1c3da151b70f70ce084b1b1c7b2d9c973805343f9.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "36459f50e9d006f7cca7cb1959302e4ae3c8c833c7a7e4d0adb5c2534df44e34", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e91a14b625a54ef3209dc56e4f8c15b181834e0d369e268944e7181dda9e0b26", "generation_seconds_batch": 20.310784847009927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7107689380645752, "target_z": 2.640624881172434, "ce": 5.919358730316162, "genuineness": 4.808597087860107, "identity": 0.7848038673400879, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/36459f50e9d006f7cca7cb1959302e4ae3c8c833c7a7e4d0adb5c2534df44e34.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "3659daa57f6a5813653167ae9015fc34eb1ed329291bfa46b239117ab35dc5da", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a35d3c4ac011b423c281f92d96b8b8bcd9c65c2759e02eab3e5c12c5bdf5cd04", "generation_seconds_batch": 21.581662795040756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2713737487792969, "target_z": 1.8281250533862976, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.6436749696731567, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3659daa57f6a5813653167ae9015fc34eb1ed329291bfa46b239117ab35dc5da.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "372089f48c88be0a63c4d6f5974310f1d22f4e9ab8c1f7e016bea339cdc2435e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25abd7aa315c8d4b87163e89349d254b8be0e0209db40007a1058d5227b88a8c", "generation_seconds_batch": 22.361298772040755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.479710817337036, "target_z": 4.062500130882536, "ce": 5.585766792297363, "genuineness": 4.582659721374512, "identity": 0.7527311444282532, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/372089f48c88be0a63c4d6f5974310f1d22f4e9ab8c1f7e016bea339cdc2435e.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "37480aaef6f08af55e31277ae50ea29787ab25af07508a4fc4d56e357b4fa2d6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4efdc419ffdfac5e6340c445f970c1850a6bf8530807d45169f4b45b02eefeb9", "generation_seconds_batch": 22.014108513016254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2093136310577393, "target_z": 3.5624999655572274, "ce": 5.919358730316162, "genuineness": 4.262581825256348, "identity": 0.506695032119751, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/37480aaef6f08af55e31277ae50ea29787ab25af07508a4fc4d56e357b4fa2d6.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "374b325b5b519ab844b53d1540860bb99aa6dc6401b257279a71e8aa49413dff", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca9d4e6b85064412efcf9793dd2e9f22948c92122a789676b1f89d8ad8407d80", "generation_seconds_batch": 16.382451524958014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6249556541442871, "target_z": 0.6328124888060989, "ce": 6.308549880981445, "genuineness": 4.7081804275512695, "identity": 0.49580442905426025, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/374b325b5b519ab844b53d1540860bb99aa6dc6401b257279a71e8aa49413dff.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "37a06c12954df5bdba65978d248e121a8cab0d6f7192016a62cdfb1e74decf37", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "419e05d7a4e8ba367a3f70e4081a169ec24520789e07e6231c6de3c249de6c51", "generation_seconds_batch": 21.763824327965267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5642099380493164, "target_z": 4.218750182546695, "ce": 5.879645347595215, "genuineness": 4.934117794036865, "identity": 0.6240248680114746, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/37a06c12954df5bdba65978d248e121a8cab0d6f7192016a62cdfb1e74decf37.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "37bbb0baaf3655fe086f63a518d260d6892d03c8e19e365ec358c512fff4637b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37d21eb2a4b7ef82289d43f3914940bcc8ae970ddd27ef94ad92972a0f1d85b3", "generation_seconds_batch": 16.235901738982648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.054304599761963, "target_z": 5.125000041331327, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.16910865902900696, "hypothesis": "Je bericht kwam dat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar, wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/37bbb0baaf3655fe086f63a518d260d6892d03c8e19e365ec358c512fff4637b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "381fabbf91978eb9fb5a7de4852a8bf3aeaf4e3adb6cd3ddc925c3b900d03ed4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86f8f5d8ca8fd0b8f3b4e5ca7baba7d0e25bf2874402e72e6ae49834aea6d5ad", "generation_seconds_batch": 21.601922195055522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7445685863494873, "target_z": 2.703124901838098, "ce": 5.804190158843994, "genuineness": 4.833701133728027, "identity": 0.6194447875022888, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/381fabbf91978eb9fb5a7de4852a8bf3aeaf4e3adb6cd3ddc925c3b900d03ed4.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "382f7931272db6375c1b9b61df876f40279166f7cf979718c1f9f30ed9391aad", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cfee7a79fb2bd79c12d8610215744413f919bb0661abd3f967974ca9c35cbe4", "generation_seconds_batch": 16.75312477594707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.783907651901245, "target_z": 4.625000316873509, "ce": 5.879645347595215, "genuineness": 4.557555198669434, "identity": 0.3420283794403076, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/382f7931272db6375c1b9b61df876f40279166f7cf979718c1f9f30ed9391aad.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "3849b4fa9542ed8c8bea3c671cdd8dfd29f5a9a1cb28547b2a77b29d366221f3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2d455e5a2d92634d7302db1d5938f320f485605be79e8ee0e7cb366f03080b65", "generation_seconds_batch": 21.61583005997818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7023191452026367, "target_z": 2.6250000964397637, "ce": 6.006728172302246, "genuineness": 4.607763767242432, "identity": 0.5110560059547424, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3849b4fa9542ed8c8bea3c671cdd8dfd29f5a9a1cb28547b2a77b29d366221f3.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "384e468948aca116668c6589ab6533853a90cf541cc8d74e83e7eb2b143c2874", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1014bde6c66dfdd6bf7b83d1f00df40f1b27ae5da5c399b0f60a495314dec8fb", "generation_seconds_batch": 14.862544005038217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.601652145385742, "genuineness": 4.356721878051758, "identity": 0.5567611455917358, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/384e468948aca116668c6589ab6533853a90cf541cc8d74e83e7eb2b143c2874.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "38874c6af45acb44422b6d9e1d0afe194573145b550eb1b623ff1b52de68e55d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7e134a33aa8396894a704b644173809f4b7a901d0624b5a9f089d8fdd2e12029", "generation_seconds_batch": 21.4460113090463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.334490031003952, "target_z": 0.09570312909007926, "ce": 6.252951145172119, "genuineness": 4.425758361816406, "identity": 0.3282189965248108, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/38874c6af45acb44422b6d9e1d0afe194573145b550eb1b623ff1b52de68e55d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "396acca5482cb2ea49f4d3fc2983b77a1fa8e95e8dd63b9505a087932208040c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "891c39119af09dc2d857bea15d6efa6dd60aeac505d9c9782fd02682febe9676", "generation_seconds_batch": 22.510171758942306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5679187774658203, "target_z": 0.5273437590412279, "ce": 6.062326908111572, "genuineness": 4.770940780639648, "identity": 0.7401944398880005, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/396acca5482cb2ea49f4d3fc2983b77a1fa8e95e8dd63b9505a087932208040c.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "39c6186872c0dab14acbd55f70a52f0627ac70dc3a04ef8b49f29709519d1158", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc2a00ae6f2ff9a3ceefdf15597cf3921e7dfe25fa43347c58cde8dd17272b19", "generation_seconds_batch": 15.290757515002042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2769129276275635, "target_z": 3.6875000068885546, "ce": 5.8875885009765625, "genuineness": 4.720732688903809, "identity": 0.7138184309005737, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/39c6186872c0dab14acbd55f70a52f0627ac70dc3a04ef8b49f29709519d1158.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "3a50fdc4d3f8908f8e25441b5ce4a2f8489f8931b3d6fc5649138b2bfaf77cbf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28fe296318cd8095eb7734be55359d75ad59b3d1b1e9d53f4bc05dc013227154", "generation_seconds_batch": 23.77611587406136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7952680587768555, "target_z": 2.796874932836593, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.3984489142894745, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3a50fdc4d3f8908f8e25441b5ce4a2f8489f8931b3d6fc5649138b2bfaf77cbf.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "3ae5bfca31c17d73c16caec3d5f6f4fbe20e2704d705b198b37f7d6321c5e89e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ffdb5b479c71778b964baa4a40d287b9f5f65cae42edd4c462841258cb7cd88", "generation_seconds_batch": 20.3020143910544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.233349084854126, "target_z": 1.7578124199205534, "ce": 6.070269584655762, "genuineness": 4.419482707977295, "identity": 0.6005628108978271, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3ae5bfca31c17d73c16caec3d5f6f4fbe20e2704d705b198b37f7d6321c5e89e.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "3b30e60c457257f49c4780316ccda3b8adc70f315522a4ffad3ab1dc28840c4b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "695469688d357103211510220e530346786c28f1ba3cfb943688a1f29b3557d0", "generation_seconds_batch": 20.44599387201015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4937000274658203, "target_z": 5.937500309984954, "ce": 4.334795951843262, "genuineness": 4.105680465698242, "identity": 0.6487840414047241, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3b30e60c457257f49c4780316ccda3b8adc70f315522a4ffad3ab1dc28840c4b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "3b854077edb1912dce7e92c235807a1b8780fb5908ecbd25333a17c9d2b24c3d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3958847421b5beeebefe746b06e08b5b366850c2e6ee2685c74ab7816eb1517b", "generation_seconds_batch": 21.763824327965267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5473101139068604, "target_z": 4.187500172213864, "ce": 5.6532793045043945, "genuineness": 4.934117794036865, "identity": 0.6484909057617188, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3b854077edb1912dce7e92c235807a1b8780fb5908ecbd25333a17c9d2b24c3d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "3bba0907b3d7446954b4d024ac5bef48cbe6ba3fd86073bf7e323032b2c874ff", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e401f8af30c366202fb2ff916cf276e48c0dbf77e2315bc6af2ad21daf5c209", "generation_seconds_batch": 21.292333215940744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4741716384887695, "target_z": 2.2031251773802794, "ce": 5.871703147888184, "genuineness": 4.507347106933594, "identity": 0.45969173312187195, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3bba0907b3d7446954b4d024ac5bef48cbe6ba3fd86073bf7e323032b2c874ff.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ef216e5446c6014110383c4cda55c35fc634b17729873215f81f55d59a3f0af", "generation_seconds_batch": 14.922703159041703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1913696825504303, "target_z": -0.16894532703054474, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.49316349625587463, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "3cb23cef073521915e5fe8299841ed8694b006c7f578bb3d0b38d08364cd58fc", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41541e81a176fb03fecae2a60219239cbbd884c7acaf2cf90e4253dd5748717a", "generation_seconds_batch": 21.54183263401501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.800807476043701, "target_z": 4.65625032720634, "ce": 5.150905609130859, "genuineness": 4.444586753845215, "identity": 0.713512122631073, "hypothesis": "Drei Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3cb23cef073521915e5fe8299841ed8694b006c7f578bb3d0b38d08364cd58fc.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "3d5fc636168e7c34dd74e5f84cfa53babe3487934ccfee29dc65139ce799d5d1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e36470cc9d426ca69770da6c9b135cdd6cfdd57fbebd8c51a9f7fd5b06dfdbd", "generation_seconds_batch": 15.287937131011859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5079712867736816, "target_z": 2.265625198045943, "ce": 6.09409761428833, "genuineness": 4.645420074462891, "identity": 0.4855991303920746, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3d5fc636168e7c34dd74e5f84cfa53babe3487934ccfee29dc65139ce799d5d1.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "3da1442b43136cb79a756cc92158a1700211d7ac175ba1394f63b31b9561d4c7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3b2cb3e068f0dd076c7fd0c6920a895a21848aeda4bfd3cd800dd457e574c17", "generation_seconds_batch": 21.592552946996875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9376022815704346, "target_z": 1.2109374595297422, "ce": 5.839932441711426, "genuineness": 4.162164688110352, "identity": 0.21089890599250793, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3da1442b43136cb79a756cc92158a1700211d7ac175ba1394f63b31b9561d4c7.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "3e98c5a719e8033aa1f99c38963b0f0c569abb342595060df79d94f9c8c6861f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ac639f104e14c1b868e4dd583c0d8f02a78a2fb202f5680d68f3180b662bd20", "generation_seconds_batch": 22.10846312204376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1501643657684326, "target_z": 3.4531251498260613, "ce": 5.998785495758057, "genuineness": 4.281409740447998, "identity": 0.42462408542633057, "hypothesis": "Ik heb het het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3e98c5a719e8033aa1f99c38963b0f0c569abb342595060df79d94f9c8c6861f.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "3eb852e8eb960b17b58aa0f0065421098a6b2f0a05fde76743c6a033e83885d1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83bfd78f7b2110c11c184936fc2d512a9968d2697f64b676de948b4425906e61", "generation_seconds_batch": 21.573268500971608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8911278247833252, "target_z": 1.1250000413313272, "ce": 6.229123115539551, "genuineness": 4.8588056564331055, "identity": 0.7179374098777771, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3eb852e8eb960b17b58aa0f0065421098a6b2f0a05fde76743c6a033e83885d1.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "3fc5cf0dd330aeedebd7348924ff1a30d551e41679caef4da9b9285f2333b53a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9f5abf786ec8d0eeaea2bd92c725b9e7921b4939f2c0dcc9732bab0d0a657c59", "generation_seconds_batch": 16.17774625099264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487090587615967, "target_z": 4.375000234210854, "ce": 4.929503440856934, "genuineness": 4.507347106933594, "identity": 0.6470402479171753, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3fc5cf0dd330aeedebd7348924ff1a30d551e41679caef4da9b9285f2333b53a.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "3fd3d194cb617908b13c899316ee344f819982e817c8a7963789415d8c745e7d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e86d319088e9a6e9b3886261cf56a6c831c85434f79f4cb7960bdae1f2871ce8", "generation_seconds_batch": 21.49833725206554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7601542472839355, "target_z": 0.8828125714687534, "ce": 6.117925643920898, "genuineness": 4.406930446624756, "identity": 0.25079643726348877, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3fd3d194cb617908b13c899316ee344f819982e817c8a7963789415d8c745e7d.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "3ffe8bbfcfb24357031a8de8930647f30663e626ad8a563e74b59b0cf7c0541b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59bdfa778022fd8c1bb989c6810af6d238a30c8104aee858e05c8d3528ea778c", "generation_seconds_batch": 21.608542587957345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9460521936416626, "target_z": 1.226562464696158, "ce": 5.839932441711426, "genuineness": 4.381826400756836, "identity": 0.669650673866272, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/3ffe8bbfcfb24357031a8de8930647f30663e626ad8a563e74b59b0cf7c0541b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "404cf0ce771a626e0126be7c01104799493e65f46a0cfc98b9f483407f5199c8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd8b56697bb89f80a2d3694182bfab27e2f6af45724ae32bfb5f95a65d58d11e", "generation_seconds_batch": 20.643091156031005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10845495760440826, "target_z": -0.3222656213404554, "ce": 6.292664527893066, "genuineness": 4.632867813110352, "identity": 0.5651988983154297, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/404cf0ce771a626e0126be7c01104799493e65f46a0cfc98b9f483407f5199c8.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "405d271b8a518bebac0d7ffe69b382571d4bf1d4a3e88fffa1e74b95e99bcfe1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "747da403e0356439766c0d5a1826bbfac44382346c333312ff4043fc274735a4", "generation_seconds_batch": 16.933936109999195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 5.847874641418457, "genuineness": 4.833701133728027, "identity": 0.7409931421279907, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/405d271b8a518bebac0d7ffe69b382571d4bf1d4a3e88fffa1e74b95e99bcfe1.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "4064110a58797e822916d112fef908dac1247a566c8159c5e364ad618845994e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c8eebbb2767a1d6aea52c885dda41d0e72d98af604155547317614102e53c38", "generation_seconds_batch": 14.86443535797298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6967798471450806, "target_z": 0.7656249225037615, "ce": 5.990842819213867, "genuineness": 4.632867813110352, "identity": 0.4610626697540283, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4064110a58797e822916d112fef908dac1247a566c8159c5e364ad618845994e.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "4154f4df4ee39f70db4de4ebbb9615ad9a012232a349b83ccd231c5253c991ea", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fd1ffa17708657fa6ccb8be6884a5f73a192a2225279e83fb084bd2e478d90e", "generation_seconds_batch": 15.420629209955223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.808161735534668, "genuineness": 4.7834930419921875, "identity": 0.5749189853668213, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4154f4df4ee39f70db4de4ebbb9615ad9a012232a349b83ccd231c5253c991ea.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "4260e59cbf997670e3d4c5488bc8d1389dd335e9f9f493ba9f86ffd7fdde57b1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "059d8ff1c5f6787c8b71cb692cd061eaff0e3d68f33198837300bbd8d1f2c268", "generation_seconds_batch": 20.51779848593287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3247017860412598, "target_z": 5.625000206656636, "ce": 5.49045467376709, "genuineness": 4.218649387359619, "identity": 0.3279128074645996, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4260e59cbf997670e3d4c5488bc8d1389dd335e9f9f493ba9f86ffd7fdde57b1.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "43496423949acb72aa2ffce2fe635fdd340c35209ddf30baff02786cbc4b39cc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7acc4ce3c27522b8195759b3d3b1536f0afa9fa434857a7bbfb0db61d87c2c25", "generation_seconds_batch": 15.244958297000267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5193318128585815, "target_z": 0.4375000344427727, "ce": 6.070269584655762, "genuineness": 4.7332844734191895, "identity": 0.7308323979377747, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/43496423949acb72aa2ffce2fe635fdd340c35209ddf30baff02786cbc4b39cc.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c2d5160b4d423739be7039dd7e7a51e398d6bde4fdce08370066c3a880712de", "generation_seconds_batch": 15.416113436105661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.831978440284729, "target_z": 1.015625005166416, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.4669581949710846, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "43cf281cd0df39c0548b2322aecd6707fed1caafe1d2fd22a39caa3f0afa732a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a0caa684542acfa0603d91c7ba0514d316bcbec2a7942183dd7f1a10987664c", "generation_seconds_batch": 20.581072889035568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.054304599761963, "target_z": 5.125000041331327, "ce": 5.0178656578063965, "genuineness": 4.519899368286133, "identity": 0.7936239242553711, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/43cf281cd0df39c0548b2322aecd6707fed1caafe1d2fd22a39caa3f0afa732a.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5ed6cc39e849a7d6b03287fd9e928c5d63663e0c645443e2c3212cd119ed469", "generation_seconds_batch": 13.482298107002862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4749697744846344, "target_z": 0.3554687573190892, "ce": 5.998785495758057, "genuineness": 4.758388519287109, "identity": 0.7354843616485596, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "447ca047ca3831c99cb06b5a12cd4e21ec7c86fb9c0bac6e3f7b3c4f5ea922a5", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e464cee28a49cae580274c12dd4e142ad8f616bb3ecd26e14b71012c8e19db7", "generation_seconds_batch": 15.503090420970693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.964266300201416, "target_z": 3.1093750361649115, "ce": 6.046441555023193, "genuineness": 4.6203155517578125, "identity": 0.6229436993598938, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/447ca047ca3831c99cb06b5a12cd4e21ec7c86fb9c0bac6e3f7b3c4f5ea922a5.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "44c990b07c368e0d9e7216419760d0f9c37144db94a9d3cb9466db569e25ab3d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b61f2ebe352412430f9dae9e915e2a036b0f4be68a9e119e1bf64f1453017100", "generation_seconds_batch": 16.6939540929161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0403153896331787, "target_z": 3.249999862228909, "ce": 5.959072113037109, "genuineness": 4.833701133728027, "identity": 0.5726714134216309, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/44c990b07c368e0d9e7216419760d0f9c37144db94a9d3cb9466db569e25ab3d.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "44e30316df5b96b284970816860415436d0de1c2be49a9b2bfe0c581813af52c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8183848a0e7278603044186bf870c382a32ddd6b689d94bf560ba76415612a1", "generation_seconds_batch": 16.752011255943216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.443000555038452, "target_z": 5.843750278986459, "ce": 5.974957466125488, "genuineness": 4.218649387359619, "identity": 0.1160319447517395, "hypothesis": "Ik schreef het nummer op de Envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/44e30316df5b96b284970816860415436d0de1c2be49a9b2bfe0c581813af52c.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "44ee154c0c45ee7fb3b38c26f801b761a928551d143cfb3d73fea2f6940d735b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e69a8e3722aeddcdee1abd79d500ea8eaea8734932f5ba435b8cc7c53cde15fd", "generation_seconds_batch": 23.651916248025373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.40920090675354, "target_z": 5.781250258320795, "ce": 5.363371849060059, "genuineness": 4.7332844734191895, "identity": 0.7309175729751587, "hypothesis": "J'ai trouvé. Elle était de boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/44ee154c0c45ee7fb3b38c26f801b761a928551d143cfb3d73fea2f6940d735b.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "44f410bcd7f1fb21d44c8fe8236e29f5caeba889b31a4c70be65c6544cb15c84", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9a440d10856f4122a1a7f5e287c5463cb7836df03845555a94949391a9a7bcb", "generation_seconds_batch": 17.08680461894255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8684065341949463, "target_z": 4.781249927670177, "ce": 5.919358730316162, "genuineness": 4.632867813110352, "identity": 0.43506598472595215, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/44f410bcd7f1fb21d44c8fe8236e29f5caeba889b31a4c70be65c6544cb15c84.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "45287aa75ae9a3107b6aca63bf00168db8ae30a6f189c4e11a94abeaebb34a49", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b7870a024bbb77d527da9c3d7ba68a1a5aa83736fbbd7c8f5e320b00a1e52f4", "generation_seconds_batch": 21.36303892498836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.403085231781006, "genuineness": 4.68307638168335, "identity": 0.4383533000946045, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/45287aa75ae9a3107b6aca63bf00168db8ae30a6f189c4e11a94abeaebb34a49.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "45579ad66feac8c510ef84cb62af9c7cfcc7d279597775fb88b72e45628119e4", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe3b31abfd21641776f2ba6565b1306ac0e95800711b3331bf4c5ea5845ada94", "generation_seconds_batch": 22.07898157904856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.682508707046509, "target_z": 4.437500254876518, "ce": 5.816103935241699, "genuineness": 4.21237325668335, "identity": 0.5814617872238159, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/45579ad66feac8c510ef84cb62af9c7cfcc7d279597775fb88b72e45628119e4.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da82553e26984e39cb749143fe61e85d20677d4f74e87bfd73cbee035bdc121a", "generation_seconds_batch": 17.008217779104598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08627393841743469, "target_z": -0.36328125990229715, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.5679184794425964, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "45fc032c1aa383ebb5eabaf8597c858508de4dfdd0186aa024566c67850ef527", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6776fd16f6179a29ace46b592c1957f9d670bc8da0e3be02001567a4a3d7402a", "generation_seconds_batch": 15.631258054985665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9529056549072266, "target_z": 4.937499979334336, "ce": 5.629451274871826, "genuineness": 4.457139015197754, "identity": 0.2891339659690857, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/45fc032c1aa383ebb5eabaf8597c858508de4dfdd0186aa024566c67850ef527.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "4609591d7ce6693040328d920db9d95bb9bd5286ebe7c5b275999c4f64cd6417", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7697cf43b2d9f624b86909610d87564efb721693d4e143f81bffaada28d78e86", "generation_seconds_batch": 19.801386415027082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6347198486328125, "target_z": 2.5000000551084365, "ce": 5.760505676269531, "genuineness": 4.7458367347717285, "identity": 0.4207741320133209, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4609591d7ce6693040328d920db9d95bb9bd5286ebe7c5b275999c4f64cd6417.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "464c2e80983ae05ff128e1ab7f2f3403990a4164d5b22204e7398f73c6dfa8df", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "036c73ebdd42c41de7e9910a0547fb77814fdb5203e8ccfdc4e6349c72b18806", "generation_seconds_batch": 16.562658303999342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6439679861068726, "target_z": 0.667968805538971, "ce": 5.982900142669678, "genuineness": 4.6203155517578125, "identity": 0.6003531813621521, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/464c2e80983ae05ff128e1ab7f2f3403990a4164d5b22204e7398f73c6dfa8df.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "47504f2304c90ce54b15bf9c79fa66c7d2ca003c789a904f462ae6e73242f1e3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "739817ba94b7f6c4f116eb0488c5926e518e1c00b8e542a8c3767290e2720c9f", "generation_seconds_batch": 22.699212047969922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5164210796356201, "target_z": 2.2812499827786135, "ce": 5.426913261413574, "genuineness": 4.607763767242432, "identity": 0.8104547262191772, "hypothesis": "La porte est encore ouverte. Je posais ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/47504f2304c90ce54b15bf9c79fa66c7d2ca003c789a904f462ae6e73242f1e3.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9d1cd400149ed9fe3802e0f0ae3e4e013f66ac45476ee516114806d3382a5c1", "generation_seconds_batch": 16.38133458804805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17130115628242493, "target_z": -0.20605468674656435, "ce": 6.109982967376709, "genuineness": 4.68307638168335, "identity": 0.8137191534042358, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "48799f5db6dd32fad44e881282c2a352220f9859d5543cd3ab8f96f2d62715fa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d612e4c9e8826338ce3e2934aa2244c37abaf4016f85515f9c4f6a755dbb9935", "generation_seconds_batch": 17.807605774025433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2241130918264389, "target_z": -0.1083984320106831, "ce": 6.181467056274414, "genuineness": 4.607763767242432, "identity": 0.3809286952018738, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/48799f5db6dd32fad44e881282c2a352220f9859d5543cd3ab8f96f2d62715fa.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "48ea8b498a58ff1ceea79ee014042c0f92e0e54ceaeb52ead627749ab0fda486", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8100f7436ba017ac5e83b653474b333f633fbdd27a2e4761a27bea7f183a6a1", "generation_seconds_batch": 19.722191301058047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2798235416412354, "target_z": 1.8437498381189683, "ce": 6.0305562019348145, "genuineness": 4.394378662109375, "identity": 0.5692006349563599, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/48ea8b498a58ff1ceea79ee014042c0f92e0e54ceaeb52ead627749ab0fda486.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "48ee9d642ac6755b709f6b3e0c21fdec4cb86541c0b28aa84df7eb38d55ab30d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aea439de0b168fe6f65784e9ad581ec20b3cc0ee443700712a1d5a162ee361fe", "generation_seconds_batch": 21.639968949952163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2629238367080688, "target_z": 1.8125000482198819, "ce": 5.657250881195068, "genuineness": 4.507347106933594, "identity": 0.625609815120697, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/48ee9d642ac6755b709f6b3e0c21fdec4cb86541c0b28aa84df7eb38d55ab30d.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "4903fcad3ca2dfe84cf614af68aff437f84c18c6003abadffeb3be4f23ee3c0e", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9cd7786c6c2996b84e56deb84e19e3ba7646c40a9fd6a3da290d803466cf1139", "generation_seconds_batch": 15.261345595936291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5755703449249268, "target_z": 2.3906247985097795, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.7783875465393066, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4903fcad3ca2dfe84cf614af68aff437f84c18c6003abadffeb3be4f23ee3c0e.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "492e809deb808bce4c2401390a889714b10634cc382c941a6a6e1de6db1ead6c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16e5c186548e508e65791e1f6984a18d108a19962e93a8e9fc73eec6eae8c700", "generation_seconds_batch": 14.964853657991625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5586705207824707, "target_z": 2.359374788176948, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.38769668340682983, "hypothesis": "The keys are on the kitchen table. I checked the drawer. It looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/492e809deb808bce4c2401390a889714b10634cc382c941a6a6e1de6db1ead6c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "496814be13c750da1b65e77bb1d1cd4801a84490892ffed36163c70c930f37c3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3e8b2a5683e5d9696bc544af14711e85543c07ef64fe46b5654bc8291327e74", "generation_seconds_batch": 22.26232389290817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7749415636062622, "target_z": 0.9101562754015449, "ce": 6.205295085906982, "genuineness": 4.7081804275512695, "identity": 0.6073265075683594, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/496814be13c750da1b65e77bb1d1cd4801a84490892ffed36163c70c930f37c3.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6687adb048bafda0fae4017d15540ff43dd686909922421b5d81df77dfd77618", "generation_seconds_batch": 15.680147695937194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1179611086845398, "target_z": -0.3046874905282375, "ce": 6.149696350097656, "genuineness": 4.419482707977295, "identity": 0.7351899147033691, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "49f880d747ac170c60bbf5843eefd3a0ed249cd240d013edefefd1ab772511b5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f444662a6a5e6f26fd8a126d860bd394268a6e2501ef2b9b463ad71b8d519a9e", "generation_seconds_batch": 21.186873442027718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8129661679267883, "target_z": 0.9804687986504165, "ce": 6.09409761428833, "genuineness": 4.7834930419921875, "identity": 0.6638482809066772, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/49f880d747ac170c60bbf5843eefd3a0ed249cd240d013edefefd1ab772511b5.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "4a013088428431bb181fb1ea74e0aa7376ca5302ba4e71f7defce3d99eeefbbd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0a4b8b5c8e2b34576d7144b0d4fc217b473cd26aa604eae6a35d5e23fdc4d60", "generation_seconds_batch": 22.6065194880357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3643226623535156, "target_z": 1.9999998897831273, "ce": 5.506340026855469, "genuineness": 4.557555198669434, "identity": 0.7445938587188721, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschieben.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4a013088428431bb181fb1ea74e0aa7376ca5302ba4e71f7defce3d99eeefbbd.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "4a3135293d10b98bdd643637c6971d13fffb09bcb42676da8ebd00ab47253979", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9d6f18528664df62999217731c4d6f39e6f60494381768abc4f909dd4ced6920", "generation_seconds_batch": 15.378730869968422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.496610641479492, "target_z": 4.093750141215368, "ce": 5.387199878692627, "genuineness": 4.3504462242126465, "identity": 0.5567878484725952, "hypothesis": "Ah les clés sont sur la table de la cuisine. Je vais regarder dans le tiroir. Et puis après la fenêtre. Prends-les quand tu partiras.", "wer": 0.2916666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4a3135293d10b98bdd643637c6971d13fffb09bcb42676da8ebd00ab47253979.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "4a46e6164ebeff620f2403adb4b81a8c77114300510287fd3214e0fe96dc2063", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cab5b5e67558055d41fc319bc68dfde05f8febb0087d0f8a49e2cc30b6a75960", "generation_seconds_batch": 21.861585121019743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5098256468772888, "target_z": 0.41992187607633663, "ce": 6.054384231567383, "genuineness": 4.532451152801514, "identity": 0.801505446434021, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4a46e6164ebeff620f2403adb4b81a8c77114300510287fd3214e0fe96dc2063.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "4a70a47cdd8b33a856f88ab3f1ceef14e58c3b406e980725dde1a1fefcea8981", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79c7a22897894d1672d70fe747c1689865a8013728024713ba358094d700506e", "generation_seconds_batch": 15.650484358076937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7783682346343994, "target_z": 2.7656249225037612, "ce": 6.022613525390625, "genuineness": 4.6705241203308105, "identity": 0.8619070649147034, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4a70a47cdd8b33a856f88ab3f1ceef14e58c3b406e980725dde1a1fefcea8981.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "4acd0642f42ccc2fafdec02e2f1fce8570b82521dba02d633f3f2d9d622de1ca", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0787e48c1ede9a8770f1833154b068d84d64e81ae57aa38ed7f4eed0a8e69122", "generation_seconds_batch": 17.08680461894255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.155703544616699, "target_z": 5.312500103328318, "ce": 5.982900142669678, "genuineness": 4.545003414154053, "identity": 0.6258918642997742, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4acd0642f42ccc2fafdec02e2f1fce8570b82521dba02d633f3f2d9d622de1ca.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "4af04387f7b83c2f969240f6bb7b10355ecf91189271104a8a668b21f3f7acd9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc6dd46f3aca6b58e3d220040c503783209644e21c11f9288748a45a2832443c", "generation_seconds_batch": 21.02312556304969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.783907651901245, "target_z": 4.625000316873509, "ce": 5.5659098625183105, "genuineness": 4.6956281661987305, "identity": 0.6271647214889526, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4af04387f7b83c2f969240f6bb7b10355ecf91189271104a8a668b21f3f7acd9.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "4b16462786c55bafc790e4ffe3b14cd3c624ac9363ce616855ede92f4c07a625", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "242d9c4fa14330e127e1f3db71dca74106c6b6d8582f5247648226a98f47388b", "generation_seconds_batch": 21.36303892498836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8853063583374023, "target_z": 4.812499938003009, "ce": 5.692992687225342, "genuineness": 4.68307638168335, "identity": 0.6236198544502258, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4b16462786c55bafc790e4ffe3b14cd3c624ac9363ce616855ede92f4c07a625.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "4bfb2eee0956b5b65accef5a8ac9c5ee376923b717671d7e591ebd6ce7a56de1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb82cb27d9319606d73285a45d4e514b057bfc50d05e7dbedc0e6d281b633909", "generation_seconds_batch": 17.013113211956806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1108254194259644, "target_z": 1.5312499552243954, "ce": 5.831989288330078, "genuineness": 4.65797233581543, "identity": 0.7332601547241211, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4bfb2eee0956b5b65accef5a8ac9c5ee376923b717671d7e591ebd6ce7a56de1.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "4c0aa6669c203f500ee09b62e769bef86ba972755f1d427db440a132217620f6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0226ca23b3264e831c2b5257a6fbf29a4d7ef4309268e964a31ad6a93ba67aaa", "generation_seconds_batch": 22.149881686083972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3276124000549316, "target_z": 3.78125003788705, "ce": 6.046441555023193, "genuineness": 4.507347106933594, "identity": 0.35343003273010254, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4c0aa6669c203f500ee09b62e769bef86ba972755f1d427db440a132217620f6.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "4c438387d5475329e413b8edf36756d89d036e420fed3d6b6b0c5458308eba24", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "33b9e9dcfc17f887695991dc0ced07f4a28513bc411e3593424886136aa305f5", "generation_seconds_batch": 16.53976989304647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13486091792583466, "target_z": -0.27343750774962383, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.40098825097084045, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4c438387d5475329e413b8edf36756d89d036e420fed3d6b6b0c5458308eba24.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "4cc34f04e8cbc2bbd3d3813de5014f976e585f6011c483942f838f071157b87b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "916146c355ace9e31dc97d9b8d2c6c8debd226ba13b17ecc9be44faa1c8ff901", "generation_seconds_batch": 16.028621101984754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5980095863342285, "target_z": 4.281250203212359, "ce": 5.665193557739258, "genuineness": 4.65797233581543, "identity": 0.5458791255950928, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame a cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4cc34f04e8cbc2bbd3d3813de5014f976e585f6011c483942f838f071157b87b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "4d689c83bb1128327ed495ef5af060828ecbcaee3050b5fd6bc25cbe4b18e20a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ce94b584aa5dee545c4cf967da8817f221a7ce4e95c5b9093692e5b70f5a886", "generation_seconds_batch": 15.83741216501221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 4.729943752288818, "genuineness": 4.2374773025512695, "identity": 0.5249874591827393, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4d689c83bb1128327ed495ef5af060828ecbcaee3050b5fd6bc25cbe4b18e20a.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "4dd84cd1a17f637aac5266ae19f27f6b1fbce87733ffc28ab4f54860443fca97", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3849ce620e8bb2a8c328d4cdc62db83287c634f04a889ab369f3152cf39dbf0a", "generation_seconds_batch": 20.445837998995557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.649308204650879, "genuineness": 4.758388519287109, "identity": 0.8641582131385803, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4dd84cd1a17f637aac5266ae19f27f6b1fbce87733ffc28ab4f54860443fca97.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "4ee8552a061248160e11968d98221303190b74b44cc6e0fa20e078b365fceca0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e79d2182751b8eea6be5a36b41a7cefffe7f37b4fb383e42a7e971c54ebf4b6", "generation_seconds_batch": 20.138355726958252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 5.593709468841553, "genuineness": 4.362998008728027, "identity": 0.3555307388305664, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4ee8552a061248160e11968d98221303190b74b44cc6e0fa20e078b365fceca0.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "4f59599cd5c64e7ebf2c5da018f925aaf0c3a460764302db0329802302d765fe", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "920811773de79d2a9629dd33fe05f9f6994cd3e9df366d86f57ba882fc14e9a9", "generation_seconds_batch": 20.339053595089354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3812224864959717, "target_z": 2.031249900115959, "ce": 5.982900142669678, "genuineness": 4.871357440948486, "identity": 0.6387427449226379, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4f59599cd5c64e7ebf2c5da018f925aaf0c3a460764302db0329802302d765fe.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "4f63b760f4ad6f1ac29df4bb61a75a5368d32699018fb4cb828bdce3d972711f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "008927de86aa831ceb4516caf7d8c4284b88959caa855a38d5ad2daa66315cfa", "generation_seconds_batch": 21.479848352028057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1530749797821045, "target_z": 1.609374981056475, "ce": 6.157639026641846, "genuineness": 4.68307638168335, "identity": 0.7193803191184998, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4f63b760f4ad6f1ac29df4bb61a75a5368d32699018fb4cb828bdce3d972711f.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "4ff525b71d3b5826640daf8ebff3048fd59ec08f573b0c1e379de0798a61eb06", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8b7be5e10c496ac742973bfa9e431132427a097de34e2acfa54775cb119f556", "generation_seconds_batch": 21.672368922969326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5404565334320068, "target_z": 0.4765624371419398, "ce": 5.879645347595215, "genuineness": 4.193545341491699, "identity": 0.5914013385772705, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/4ff525b71d3b5826640daf8ebff3048fd59ec08f573b0c1e379de0798a61eb06.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "501ecf0cc0dbb8125d80c1199bba62b1eb79d30269ace194d2d668f4175be3b4", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2e679ba05736b925400a38322284c4b4aa6bc7bb5d2a1bdfe2c5a67958438b23", "generation_seconds_batch": 15.75637153792195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9698054790496826, "target_z": 4.9687499896671685, "ce": 5.458683967590332, "genuineness": 4.645420074462891, "identity": 0.7162801027297974, "hypothesis": "Más llaves están en la mesa de la cocina, miren al cajón, y luego junto a la ventana llévatelas cuando te vayas.", "wer": 0.17391304347826086, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/501ecf0cc0dbb8125d80c1199bba62b1eb79d30269ace194d2d668f4175be3b4.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "5025d0efc91e7f4a30aae75f72048574c8fc1d295252491d2e95dfeb078d2eed", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e013403b72cd58c5e997df9497044a7ceea065b2a4fe99d4327833a991f864f", "generation_seconds_batch": 14.841357325902209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1741998195648193, "target_z": 1.6484376041893873, "ce": 6.221180438995361, "genuineness": 4.375550270080566, "identity": 0.3932676911354065, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5025d0efc91e7f4a30aae75f72048574c8fc1d295252491d2e95dfeb078d2eed.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "50660932e0b36a3119d3239dab57f5bc26f54ae74f75f677c38cdbd3d2ff7e13", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7688eb00681f4814a6548f02ff39dafb791c6047791c91963245c51b939e84d", "generation_seconds_batch": 21.207572338054888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39997681975364685, "target_z": 0.2167968640213662, "ce": 6.0146708488464355, "genuineness": 4.482243061065674, "identity": 0.2917965352535248, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/50660932e0b36a3119d3239dab57f5bc26f54ae74f75f677c38cdbd3d2ff7e13.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "508b6b0d199861d35c912bcc484897892c1311ed74b422fb0f3c511ca1c991e5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad70663be1538f486a67d7d37b59d0668597fdebc07f0d672726eb3054949981", "generation_seconds_batch": 21.539820856996812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1670641899108887, "target_z": 3.4843751601588933, "ce": 5.824047088623047, "genuineness": 4.331617832183838, "identity": 0.7604784369468689, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/508b6b0d199861d35c912bcc484897892c1311ed74b422fb0f3c511ca1c991e5.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "50a73a43e369ee611925c8d03dce17939efa0ba0ef3b68758bc41230c2b97b2e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b553a49dbaee08a622ece1c27928a9b34f6641dc3f353bc3917f6c683f977ab", "generation_seconds_batch": 22.112113479990512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6347198486328125, "target_z": 2.5000000551084365, "ce": 5.363371849060059, "genuineness": 4.632867813110352, "identity": 0.597724437713623, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/50a73a43e369ee611925c8d03dce17939efa0ba0ef3b68758bc41230c2b97b2e.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "50ae0ed14b6e341d933ce390eb1e6d7c4c9165e42a77b33efef3a8604f43e7bf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2758450529257e8ee82639058cc28c36cdecc4a5ba26a2757448be1352574049", "generation_seconds_batch": 19.646250017918646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7361187934875488, "target_z": 2.687500117105427, "ce": 5.462655067443848, "genuineness": 4.833701133728027, "identity": 0.5231122970581055, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/50ae0ed14b6e341d933ce390eb1e6d7c4c9165e42a77b33efef3a8604f43e7bf.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "5160879415be1692d57cd1763e030f11b909876bd42989f4a6fe2e9e8bb2bffd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a400aee3b03a84731d4b3596cd4ec2eb46853a1196594b3f4bb9deb56ad8a211", "generation_seconds_batch": 21.134925603982992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5980095863342285, "target_z": 4.281250203212359, "ce": 5.514282703399658, "genuineness": 4.65797233581543, "identity": 0.5434596538543701, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5160879415be1692d57cd1763e030f11b909876bd42989f4a6fe2e9e8bb2bffd.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "51df773b32bc23da8ca854f8e868f58ba292eed83a97f2e791b33ba25da836c0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0d406bc5a95e6aa5e9619dd40b1b1d3f08871dfec6e308f5a1498f5b03a65a0", "generation_seconds_batch": 21.464500084053725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7390294075012207, "target_z": 0.8437499483358409, "ce": 5.847874641418457, "genuineness": 4.7332844734191895, "identity": 0.6874001026153564, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/51df773b32bc23da8ca854f8e868f58ba292eed83a97f2e791b33ba25da836c0.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "5204c127ed9edbb94588cace028ccd392a3a36dc36ec607bbf3f1763a1ceef3f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "882993b7ccbf1c535794f89db300244c0c7e73ea53ed2ca64d1289dbe5ac48ec", "generation_seconds_batch": 22.86662848200649, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5473101139068604, "target_z": 4.187500172213864, "ce": 5.561938762664795, "genuineness": 4.6956281661987305, "identity": 0.6603661775588989, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5204c127ed9edbb94588cace028ccd392a3a36dc36ec607bbf3f1763a1ceef3f.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "52354ff8d5db3bf0315cb9dc0ac4969bfd1e09c7bec1f646e7a85931b4c29726", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e49fdd4122e20d97fdd287bf904310e6423a7b5336d6d3a2f7da58b42bf9329", "generation_seconds_batch": 15.328862956026569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3698620796203613, "target_z": 3.8593752841528746, "ce": 6.0305562019348145, "genuineness": 4.632867813110352, "identity": 0.36686229705810547, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten net naar de lunch terug.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/52354ff8d5db3bf0315cb9dc0ac4969bfd1e09c7bec1f646e7a85931b4c29726.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "5246daf43790f7d69aa2546e936dbd99d6be6592a62a6b0b6359860d49ade859", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2715d8bb4ce655e58677420d0ad22526dd2716130d5c8ad9c22bad6524d807d", "generation_seconds_batch": 22.172967030084692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1726033687591553, "target_z": 5.34375011366115, "ce": 5.6532793045043945, "genuineness": 4.193545341491699, "identity": 0.5503613352775574, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5246daf43790f7d69aa2546e936dbd99d6be6592a62a6b0b6359860d49ade859.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "52b963a35d0198be2a0e2d412721e99ed197bf6acb9374df8df4434c2f5b7f4d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08564f80f570a3434aa99906c9c2bf3b9b3fdf56da9667fe45c58baa2fb604bb", "generation_seconds_batch": 20.79976037296001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5679187774658203, "target_z": 0.5273437590412279, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.14138385653495789, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/52b963a35d0198be2a0e2d412721e99ed197bf6acb9374df8df4434c2f5b7f4d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "52d08d21c59c9f37778b46e2e3ec7018a9233a7a0c75be40784d68b4b06789c7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85b770f49e8d3874a4447ccc1cff9cd2e3d10c103d50a607ae26c89ea13994e4", "generation_seconds_batch": 16.359595753950998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9896159172058105, "target_z": 3.1562498312304137, "ce": 5.287916660308838, "genuineness": 4.632867813110352, "identity": 0.7716817855834961, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/52d08d21c59c9f37778b46e2e3ec7018a9233a7a0c75be40784d68b4b06789c7.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "52f1101dd1815db2bc19e549cac73bf64113ce3f2acfe90d44c856268b11b6e7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30eefd3806407c8d6c943fd48381029c0e2d532d8899f2b6c344694ed3987b1d", "generation_seconds_batch": 21.087776396074332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9629520177841187, "target_z": 1.2578124750289899, "ce": 5.597680568695068, "genuineness": 4.507347106933594, "identity": 0.6162590980529785, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/52f1101dd1815db2bc19e549cac73bf64113ce3f2acfe90d44c856268b11b6e7.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "52f2e8d69eee35a61f28644ecd23199907245850505e9c0bbb64780c476ee947", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "14ec70ed100143262b0d3d35bd1dd754623c44770abef26dc1c3c9ce3d7a0ada", "generation_seconds_batch": 21.712247720104642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2402026653289795, "target_z": 5.4687501549924775, "ce": 4.99999475479126, "genuineness": 4.2751336097717285, "identity": 0.4676598608493805, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/52f2e8d69eee35a61f28644ecd23199907245850505e9c0bbb64780c476ee947.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "532482b115a807746ab09b0f7d1e6cfa9e918a3f8ed3d369ea8d01f65afd8a6b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb70da9652d5b8481ddd2ba4e050bba7e9964c16a7172c18fe3c0be9ceaa83dd", "generation_seconds_batch": 22.131375003024004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8628673553466797, "target_z": 2.9218749741679204, "ce": 6.0305562019348145, "genuineness": 4.400654315948486, "identity": 0.4382604956626892, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/532482b115a807746ab09b0f7d1e6cfa9e918a3f8ed3d369ea8d01f65afd8a6b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "534a1b65a499f1af32a5e5784b641595b35d2fc8e06b311fc86b82d48b46944f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c23b166962cd85fcdf676fc717a1b8e7e8bf6d4005f38cc681b116f3f768f83c", "generation_seconds_batch": 21.598469011951238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 5.34748649597168, "genuineness": 4.6956281661987305, "identity": 0.8311981558799744, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/534a1b65a499f1af32a5e5784b641595b35d2fc8e06b311fc86b82d48b46944f.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "53c0e04f3bf094aa90244e39dc65ab332d960664560d4f310ce899ccde19fed8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b43d8674b7bfa8bfc7f7148d462b8623c45db1db3998fe49db0d5d2b59bcb54", "generation_seconds_batch": 21.27539683005307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1699748039245605, "target_z": 1.6406249913893067, "ce": 6.038498878479004, "genuineness": 4.758388519287109, "identity": 0.7411229610443115, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/53c0e04f3bf094aa90244e39dc65ab332d960664560d4f310ce899ccde19fed8.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "5408438638ad09a6b7bea47530440488f447a22ba7622b640b489f6fe7025fe1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f54f6bed47c8196e1df647cd14ee68c3481ab07cbc91f26faf2551fea82ac7be", "generation_seconds_batch": 20.7737854529405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42532655596733093, "target_z": 0.26367187952061394, "ce": 5.736677646636963, "genuineness": 4.494794845581055, "identity": 0.4324433207511902, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5408438638ad09a6b7bea47530440488f447a22ba7622b640b489f6fe7025fe1.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f569c0106cba2051674e6e3fb461851d3412c9cdf0d08d990bd2bee7f3557e9b", "generation_seconds_batch": 17.008217779104598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0904988944530487, "target_z": -0.3554687573190892, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.6055785417556763, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "54780195f72f06ee3069e646bf123fbe34d731775ebe4382d1f59dbff9b2dd02", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d2da017294361d8081c6655304ffe74b0ed20ea4104c6e64c6b7a14dd607d7e3", "generation_seconds_batch": 16.400512019055896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0854756832122803, "target_z": 1.4843749397251478, "ce": 5.2045183181762695, "genuineness": 4.243753433227539, "identity": 0.24498173594474792, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/54780195f72f06ee3069e646bf123fbe34d731775ebe4382d1f59dbff9b2dd02.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "54847745cf9fccedd6b51704de5340bf0a8b22a3fde0d8dbd7ff69e5d53bbd19", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2228e47a582c03f6ed12cede23decc1c83c77067685460f3fc07980f14c50e4a", "generation_seconds_batch": 22.779486375977285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8853063583374023, "target_z": 4.812499938003009, "ce": 5.2918877601623535, "genuineness": 4.6956281661987305, "identity": 0.7492339611053467, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de là. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.2631578947368421, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/54847745cf9fccedd6b51704de5340bf0a8b22a3fde0d8dbd7ff69e5d53bbd19.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "5595446de39665ebc7f3bd6ec7c7f7aa9131430a96a41f34cabfc9c80f4026af", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4e2980826c2b59c9aa8fc97679cc47eab82342fcb2a9cd19874e2887c8c0132", "generation_seconds_batch": 21.87470562395174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20932574570178986, "target_z": -0.13574219105191093, "ce": 6.348263263702393, "genuineness": 4.796044826507568, "identity": 0.6007245779037476, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5595446de39665ebc7f3bd6ec7c7f7aa9131430a96a41f34cabfc9c80f4026af.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "55f94de6d73f2867921685f17f96cb8d0e241a9d864ada11861cfe3333253e9e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12cb72167fa073951347d06f138556854fbd17841efcc96cdf9f9ec815f2eac8", "generation_seconds_batch": 21.450998093932867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5473101139068604, "target_z": 4.187500172213864, "ce": 5.657250881195068, "genuineness": 4.545003414154053, "identity": 0.4301641583442688, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/55f94de6d73f2867921685f17f96cb8d0e241a9d864ada11861cfe3333253e9e.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "5605c1184d9453604dd774e8ef3c294b6ba7649b3f1208caf27045babb521fc4", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0b8303cb3005dd5ff0340b5e76315415df90c8873c5346e9bce0c704f0e18d53", "generation_seconds_batch": 16.78469371504616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5980095863342285, "target_z": 4.281250203212359, "ce": 5.895530700683594, "genuineness": 4.494794845581055, "identity": 0.596849799156189, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5605c1184d9453604dd774e8ef3c294b6ba7649b3f1208caf27045babb521fc4.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "56224328b1ed3947c323a015d1defd16aad07b150bb266ddda0f6be83e33527b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eae6a20e1e933beb035772fee1d87a6d12f799a0a0ec3c1493ffad0fb0bef584", "generation_seconds_batch": 21.30017559591215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5642099380493164, "target_z": 4.218750182546695, "ce": 5.311744689941406, "genuineness": 4.645420074462891, "identity": 0.6571905016899109, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, comme tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/56224328b1ed3947c323a015d1defd16aad07b150bb266ddda0f6be83e33527b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "565cb157ea56ab8af4d9f894569e80736dd6fb94cdd757a3d2d96305848d2ecf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c50cb501f9add8b8e38d309680f879724becc922241a487086b45f85fb7d9aef", "generation_seconds_batch": 15.689396557048894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4036617279052734, "target_z": 3.9218753048185384, "ce": 5.49045467376709, "genuineness": 4.984326362609863, "identity": 0.5877348780632019, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/565cb157ea56ab8af4d9f894569e80736dd6fb94cdd757a3d2d96305848d2ecf.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "56bf9fbad4b9470047cafabc10eb4f78267fb42d1648e7253d00624e2fbcb5fd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e837b742ffe3e3bb9eb3334008fa65a705a51dd747a219b369fd682aa89a4d6e", "generation_seconds_batch": 20.926585896057077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1895031929016113, "target_z": 5.375000123993981, "ce": 5.279973983764648, "genuineness": 4.65797233581543, "identity": 0.6145855784416199, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/56bf9fbad4b9470047cafabc10eb4f78267fb42d1648e7253d00624e2fbcb5fd.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "56f383cf213948289fc5a92a8e40bb65ca77db03e3b22a740c38d57758477e7b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97023b333bb6d7e475592dae0b6b15ab18af3913afb8379729eb0ff1a8cff1aa", "generation_seconds_batch": 22.311523201991804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.412111520767212, "target_z": 3.937500089551209, "ce": 6.0146708488464355, "genuineness": 4.796044826507568, "identity": 0.6360529661178589, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/56f383cf213948289fc5a92a8e40bb65ca77db03e3b22a740c38d57758477e7b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "57040df1455c0c0fdede77da29c60cffba6dffb03d79c05d9d2778be589ef4e8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f383d10ee4cef93f0620a685cd5c37b991c0931389b67f4b088c11b0b3e4b556", "generation_seconds_batch": 22.976312109967694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2262134552001953, "target_z": 3.5937499758900593, "ce": 5.982900142669678, "genuineness": 4.758388519287109, "identity": 0.5664933919906616, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/57040df1455c0c0fdede77da29c60cffba6dffb03d79c05d9d2778be589ef4e8.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "5778b6e17102183cd3c92d04b0aeb0c38ce110dc4c4345b59abb3b759ba01309", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e7996ff972d490dd741e5765d29543dc1ce2ecad0ef3a87459b0bc91996f540", "generation_seconds_batch": 14.998238055966794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5333209037780762, "target_z": 2.3124999931114454, "ce": 5.8875885009765625, "genuineness": 4.758388519287109, "identity": 0.7333821058273315, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5778b6e17102183cd3c92d04b0aeb0c38ce110dc4c4345b59abb3b759ba01309.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "57bc19e896f87059af2f295517cc90feb7cbc1af86addb19856b2e7f9f86c36d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38368dc8216521068b5323697da7497db99c2f40584e7d90d79409f7ceccd40b", "generation_seconds_batch": 20.51779848593287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.054304599761963, "target_z": 5.125000041331327, "ce": 5.5738525390625, "genuineness": 4.256305694580078, "identity": 0.37564051151275635, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/57bc19e896f87059af2f295517cc90feb7cbc1af86addb19856b2e7f9f86c36d.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "57bf1089fa8b90fb0994f99fb7979b7cceb4174a0d866da21e30d3dd6504f81a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36fec76980a955956e07c90b0dec258740cbc5f6d1d5c848d89615a8586e2aa2", "generation_seconds_batch": 20.966576074948534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.786818265914917, "target_z": 2.7812501481039225, "ce": 6.022613525390625, "genuineness": 4.7081804275512695, "identity": 0.6301202774047852, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/57bf1089fa8b90fb0994f99fb7979b7cceb4174a0d866da21e30d3dd6504f81a.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "57e13190b4554a151ed2f024f792ca8713a07a67f4c94db8b5a2b8b26da57080", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7dc207ce17945cb229534e9f27329a02bc9be1bbf676af5819249915b086392", "generation_seconds_batch": 20.62316119496245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3896725177764893, "target_z": 2.04687512571612, "ce": 5.8875885009765625, "genuineness": 4.8588056564331055, "identity": 0.7898893356323242, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/57e13190b4554a151ed2f024f792ca8713a07a67f4c94db8b5a2b8b26da57080.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "57fa06b27a0cd9c7df663ef28ab861e5bdbb28a8a8eb7aaba5b0d0fa4f0ff6bc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e91ebcc7fcbead3dc0f109cb5c622b8f4cdc7fe407a56ea08eb9a5ad6672c1c6", "generation_seconds_batch": 20.52542274899315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5869311094284058, "target_z": 0.5625000757740999, "ce": 5.8875885009765625, "genuineness": 4.055472373962402, "identity": 0.23335236310958862, "hypothesis": "The door d is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/57fa06b27a0cd9c7df663ef28ab861e5bdbb28a8a8eb7aaba5b0d0fa4f0ff6bc.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "58bc1800111638fb04a1c36d7e265743f8a4a59e1c14d39996e0b2ac2e049592", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c7e8bfff5902b20ec4d6c1396543cc74112047ac48762cfa7b596958f9d45f8", "generation_seconds_batch": 21.639599507907405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.429011344909668, "target_z": 3.968750099884041, "ce": 5.967014789581299, "genuineness": 4.394378662109375, "identity": 0.4582752585411072, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/58bc1800111638fb04a1c36d7e265743f8a4a59e1c14d39996e0b2ac2e049592.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "58cf4fe519d9bab1603c5b7d05f824a86807575ae588a8584e3bca589094d1ec", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "382e661fbfa9710b01a05dd9cdf162bf61594a959a380bc2beeb9b2133ea4f69", "generation_seconds_batch": 16.382451524958014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2558002471923828, "target_z": -0.04980469019084162, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.15855059027671814, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/58cf4fe519d9bab1603c5b7d05f824a86807575ae588a8584e3bca589094d1ec.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "58e5379ad7a4fdedd149cc9b382252ea91bd8d4c9cc8449acfc025ba8de47f45", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6dffb145beb9d374e42c9028c06c20a59cb36150c120479687261b85f44de409", "generation_seconds_batch": 20.982883992022835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6119985580444336, "target_z": 6.156249941447286, "ce": 5.019851207733154, "genuineness": 4.093128204345703, "identity": 0.5406441688537598, "hypothesis": "Me he encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/58e5379ad7a4fdedd149cc9b382252ea91bd8d4c9cc8449acfc025ba8de47f45.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "58ec4904de47f8d9f8e08b6b7e76ade0c0939b5b8ff250abdc3a1c8172f7b5f8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "148dc5f1bac4ecfe42b6662bf1ab0c54effa522144585bd844c4e957c78b7cc5", "generation_seconds_batch": 23.1543828350259, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1596825271844864, "target_z": -0.22753906885038622, "ce": 6.1894097328186035, "genuineness": 4.570107460021973, "identity": 0.4861602187156677, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/58ec4904de47f8d9f8e08b6b7e76ade0c0939b5b8ff250abdc3a1c8172f7b5f8.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "591a8d3a47d8e75572b7e2484f4c4a1f4d340ade488e749e19430d025d11d422", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a657929de4787076fd2576bc48a4c36dac299daa7c96d6047009bf92a230380", "generation_seconds_batch": 23.63110160792712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.626269817352295, "target_z": 2.4843748295082753, "ce": 5.863759994506836, "genuineness": 4.645420074462891, "identity": 0.7672967314720154, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/591a8d3a47d8e75572b7e2484f4c4a1f4d340ade488e749e19430d025d11d422.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "595d0ee716c4739b52407cd9ab0b62421719aad8fa65757f384de3880cf0860e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c85e12161dde8b3c63a06ec7ecd771e683cc80ce5e6694baf17cb1e370e7ca07", "generation_seconds_batch": 16.17774625099264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2233028411865234, "target_z": 5.437500144659645, "ce": 5.202532768249512, "genuineness": 4.595211505889893, "identity": 0.6188784241676331, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/595d0ee716c4739b52407cd9ab0b62421719aad8fa65757f384de3880cf0860e.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "59b1a5e45898c91883d277a6fe1954f14ff9c8e6912f145966e5a80d405c7b5b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd6fe9cd43087988edb3fbdc4a52e0cd43c8a397f645c9afdc81b68c1f5f8635", "generation_seconds_batch": 16.712107360945083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.138803720474243, "target_z": 5.281250092995486, "ce": 5.462655067443848, "genuineness": 4.419482707977295, "identity": 0.6499761343002319, "hypothesis": "Non, mon message est arrivé après mon départ. Je l'ai relevé. Puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/59b1a5e45898c91883d277a6fe1954f14ff9c8e6912f145966e5a80d405c7b5b.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "5af527ae3c31b34b25571773383333d4f51cced0765d340724cafdfa5952c8a0", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "af61f4893de8fd65b1fdcca58cc469fd9fff33db8b918f260b6832b7bf30377a", "generation_seconds_batch": 17.915229376987554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3698620796203613, "target_z": 3.8593752841528746, "ce": 5.40705680847168, "genuineness": 4.65797233581543, "identity": 0.38841983675956726, "hypothesis": "La carretera gira a la izquierda tras el puente, así que hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5af527ae3c31b34b25571773383333d4f51cced0765d340724cafdfa5952c8a0.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "5af6122037ef9852e36f47f9c9245d17eb4154732fc8d30b1222c7e8dc98644e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35399baa3b27391ba955ff981728a55a4d3f89723fdc79fed2fe4e65a270455e", "generation_seconds_batch": 15.779951466945931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.728734970092773, "genuineness": 4.796044826507568, "identity": 0.7208877801895142, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5af6122037ef9852e36f47f9c9245d17eb4154732fc8d30b1222c7e8dc98644e.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "5b1587a6b14ed26547f6086aab34fd3bd5556c603b8168c63f2ad41d269bc94c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5000fbd982644f699fdb8893e1cf00e2ecc9dba6c13233a8c794d2f30e51ba63", "generation_seconds_batch": 16.987118953024037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.681078910827637, "genuineness": 4.7458367347717285, "identity": 0.8605890274047852, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5b1587a6b14ed26547f6086aab34fd3bd5556c603b8168c63f2ad41d269bc94c.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "5b82e52ac7de0c5cd2715247df2aed0707e3c9e61ae743b446eefe3f77e70aa5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9fb197ef508e2da4d4cbd8fb21e58a224e1936ac741cf18988b54289c81119e", "generation_seconds_batch": 15.484503711923026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.234663486480713, "target_z": 3.6093752014902205, "ce": 5.95112943649292, "genuineness": 4.494794845581055, "identity": 0.195994034409523, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5b82e52ac7de0c5cd2715247df2aed0707e3c9e61ae743b446eefe3f77e70aa5.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "5beccb3b550979301d18f899cb3303810c64d3f49fe4dcd19477dcbf64583aaa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a25b45f8946ea85a7dea2af0b75e34e062b03fb731d6c66929630808d618fc1", "generation_seconds_batch": 21.70256960694678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3247017860412598, "target_z": 5.625000206656636, "ce": 5.824047088623047, "genuineness": 4.293961524963379, "identity": 0.27485141158103943, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5beccb3b550979301d18f899cb3303810c64d3f49fe4dcd19477dcbf64583aaa.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "5bfe83458f23edc55a39e4a27dc81f21a5c439bbfa8a662a0c14e49ae2314597", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dd1885154c086ac5378151ab57a72918f4c07c159626b04961593186660e75d2", "generation_seconds_batch": 14.676003309083171, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0318655967712402, "target_z": 3.2343750774962388, "ce": 6.022613525390625, "genuineness": 4.494794845581055, "identity": 0.31726619601249695, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5bfe83458f23edc55a39e4a27dc81f21a5c439bbfa8a662a0c14e49ae2314597.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "5c1b8e2bf0aec552b21b1d5b96765e70a403fc7e3a01c1894fa5cf310cae60ff", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3579bf33dfa71073725cbd0dcf3e63e6ddfb8838667e0462f1b897b4798f01d4", "generation_seconds_batch": 15.476135998032987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1528169810771942, "target_z": -0.24023437177099005, "ce": 6.308549880981445, "genuineness": 4.65797233581543, "identity": 0.5935655832290649, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5c1b8e2bf0aec552b21b1d5b96765e70a403fc7e3a01c1894fa5cf310cae60ff.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "5c823c5c0d4ed4c71edc32b4a0ff85b255e1f4e69891df8ded3843fb24f7bac2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a56e7504bf9164b62e08cc62ad688268ed6ae3b91a7f4d8f58807a5b9ef18316", "generation_seconds_batch": 21.418708279030398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.288273572921753, "target_z": 1.8593750637191295, "ce": 6.078212261199951, "genuineness": 4.281409740447998, "identity": 0.3893543481826782, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5c823c5c0d4ed4c71edc32b4a0ff85b255e1f4e69891df8ded3843fb24f7bac2.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "5ce1edf01e067d55747be5803ddfd7ae4d6479596d42832ac67b6e9e89b77c92", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dd52d8f43a49d938d23e55f14ba9a33064fb5273ed0daa8758ab4ebd3e7211ac", "generation_seconds_batch": 22.6137688489398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750108003616333, "target_z": 4.562500296207845, "ce": 5.238275051116943, "genuineness": 4.545003414154053, "identity": 0.5704423189163208, "hypothesis": "Les gliss sont sur la table de la cuisine, j'ai regardé dans le tiroir, plus près de la fenêtre, prends-les quand tu partiras.", "wer": 0.08333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5ce1edf01e067d55747be5803ddfd7ae4d6479596d42832ac67b6e9e89b77c92.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "5ce7f604b9d3b2b91d100feaa8501d4204eba15d2b5bf52f58744b859e403fc8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64083be4f1d54b870f4bb1f11aafa65fe5aa1a61a81f8dfa0fccfdf64c17804e", "generation_seconds_batch": 21.639968949952163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7897288799285889, "target_z": 0.9374999793343364, "ce": 6.0146708488464355, "genuineness": 4.7834930419921875, "identity": 0.6573578715324402, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5ce7f604b9d3b2b91d100feaa8501d4204eba15d2b5bf52f58744b859e403fc8.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "5cf516d6fef0d4fda1c95421acb19b64130536365aab1c3c69db4be657e4560f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e3db241344937ad79662b776dd3de685dd342cc6e8ab2ddf932d4f8f216d115", "generation_seconds_batch": 16.905436469009146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.7128496170043945, "genuineness": 4.21237325668335, "identity": 0.3589975833892822, "hypothesis": "De sleutels liggen op de keukentafel. Een kikje in de la. En daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5cf516d6fef0d4fda1c95421acb19b64130536365aab1c3c69db4be657e4560f.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "5cf94062d05b6da25fd3a5e236d6f5def92e773e46f95d7b3d9e0029238de449", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7e16582f26ac4611c9ffed1aa74afc0a3cf4c2ffac32fdc5b2447e231b335c8", "generation_seconds_batch": 21.292333215940744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4910714626312256, "target_z": 2.2343751877131113, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.44422560930252075, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5cf94062d05b6da25fd3a5e236d6f5def92e773e46f95d7b3d9e0029238de449.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "5d13cfa43fa083ee0429cacdd74b42a686f82b883c253d69b15243cc5c3aa681", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b60a564b9a04dcdbbcb1d1d8adb9f9daa7fe475ecfc788f7a6a4079042472b0c", "generation_seconds_batch": 22.669840955059044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9529056549072266, "target_z": 4.937499979334336, "ce": 5.212460994720459, "genuineness": 4.394378662109375, "identity": 0.6464939117431641, "hypothesis": "Me he encontrado la cajita, estaba junto la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.11764705882352941, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5d13cfa43fa083ee0429cacdd74b42a686f82b883c253d69b15243cc5c3aa681.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "5d52fda4265155782c5786f3861b9a00c0d5991071aa4dd19dc852cbd446d124", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "137a5ea6c2c2b7a59e45b21c902fcc9c70cab8e2abbe31eeea42f3d1294e2f0e", "generation_seconds_batch": 19.758079020073637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 6.0146708488464355, "genuineness": 4.921566009521484, "identity": 0.8028173446655273, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5d52fda4265155782c5786f3861b9a00c0d5991071aa4dd19dc852cbd446d124.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "5d6cdfdb07fb3e2391de2cde6bb2a9e670b088ef270208d169d5d5fa7eeeee09", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ae2fef50292fde2c881a89310223a12d83d0d4dbeed10fe5bae6c1b97c601fd", "generation_seconds_batch": 22.589740323019214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767007827758789, "target_z": 4.593750306540677, "ce": 5.847874641418457, "genuineness": 4.545003414154053, "identity": 0.8394855856895447, "hypothesis": "Jemand hat den kleinen Plauenstuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5d6cdfdb07fb3e2391de2cde6bb2a9e670b088ef270208d169d5d5fa7eeeee09.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db8ced2aacf6a383eca5ff8b23ac17a0f1c4376491832d3c86772312279f2e74", "generation_seconds_batch": 16.418740987894125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1868746280670166, "target_z": 1.6718750017221387, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.7368557453155518, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "5e373dd20d81ef3fcc5d8f8c0805bfa406ba1686ee5eec9b1c0029c36468dcc0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5627873c40fbc78c65510172e4b80d807f04bde875a68321568843d29c0ab62", "generation_seconds_batch": 22.921484602964483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3078019618988037, "target_z": 5.593750196323804, "ce": 5.3792572021484375, "genuineness": 3.961331605911255, "identity": 0.32604485750198364, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5e373dd20d81ef3fcc5d8f8c0805bfa406ba1686ee5eec9b1c0029c36468dcc0.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "5edd89d8cb12957a187627504103d9c5167958f808f4a93e00fee694768fe7fc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9a56b8576478bd55b67bd04501a24fc93c3aef06cc208f3a23c8509577ce009a", "generation_seconds_batch": 25.519694881979376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071204423904419, "target_z": 5.156250051664159, "ce": 5.831989288330078, "genuineness": 4.7458367347717285, "identity": 0.7715333700180054, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5edd89d8cb12957a187627504103d9c5167958f808f4a93e00fee694768fe7fc.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "5ee312be645dbf9227220063b4338f36c3ba68bbc405ff50396260a51d7b147a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "011e4bf277e631612f4b71efd860d2208f73a9640fb869067f8b7b6fb32edd6e", "generation_seconds_batch": 23.88617042498663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.496610641479492, "target_z": 4.093750141215368, "ce": 5.990842819213867, "genuineness": 4.7332844734191895, "identity": 0.8012710213661194, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5ee312be645dbf9227220063b4338f36c3ba68bbc405ff50396260a51d7b147a.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "5ef2726a6b4d4376b9828b956b33004d019dd339c9fdf8c9a68dff869ba0bcad", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "572b087da8f603832fa8a12b08865efbaa858ebcaf375b4063d6d774d74e7a9b", "generation_seconds_batch": 15.735806331038475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9698054790496826, "target_z": 4.9687499896671685, "ce": 5.935244083404541, "genuineness": 4.758388519287109, "identity": 0.5184959173202515, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5ef2726a6b4d4376b9828b956b33004d019dd339c9fdf8c9a68dff869ba0bcad.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "5ef6a90e8e8f0a7e5d1b91e609dfc1061f788175271dc2d4e08d1adc16d384a6", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c704b27b56f02c0e8c0f520813a95340873cb8c2efb6abb410ec5435030d681", "generation_seconds_batch": 16.235901738982648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5612990856170654, "target_z": 6.062499910448791, "ce": 5.903473377227783, "genuineness": 4.394378662109375, "identity": 0.45123526453971863, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer. Legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5ef6a90e8e8f0a7e5d1b91e609dfc1061f788175271dc2d4e08d1adc16d384a6.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "5f41a1afa6b7430a1f49de5a46ec7c54c342088e6bd5998c3301bdd2fb8695da", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f90b176f9dfb624f26d02af4d1e1cea8842a8c141633d9a34ba19c34825be21a", "generation_seconds_batch": 21.734626968041994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.676969289779663, "target_z": 2.5781248605067706, "ce": 5.919358730316162, "genuineness": 4.337893962860107, "identity": 0.2762870192527771, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5f41a1afa6b7430a1f49de5a46ec7c54c342088e6bd5998c3301bdd2fb8695da.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "5f45e6604a9899f961112f7d21d9811d4acb1a9cbcb3fb8716565cac7419741f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ec543f9a1fd779a8b16d71761dc1a70bc980feba41f0fcac7c706ef89171a6f", "generation_seconds_batch": 21.49833725206554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7517043352127075, "target_z": 0.8671875663023374, "ce": 6.133810997009277, "genuineness": 4.337893962860107, "identity": 0.4909409284591675, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5f45e6604a9899f961112f7d21d9811d4acb1a9cbcb3fb8716565cac7419741f.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "5f9e6308f4b3ab23c9adeef8f8ae0de00ab49d97b25a12e1ce6606effe6b6479", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76389250ed14cff9708f2849e8260db5e281e13b0d160970c4298490d760316e", "generation_seconds_batch": 15.614563695038669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19823524355888367, "target_z": -0.15624999655572272, "ce": 6.1020402908325195, "genuineness": 4.7081804275512695, "identity": 0.79825758934021, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5f9e6308f4b3ab23c9adeef8f8ae0de00ab49d97b25a12e1ce6606effe6b6479.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "5fb543c200d4b5e77964b95f7f6b36d112be49a6bfd5ec9b206f4f2582c6d011", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c5d5ef6a198639ace37cf1cff4908ed16e5a12a59980a16c79c38db00d67e6fc", "generation_seconds_batch": 18.30658068100456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6656088829040527, "target_z": 4.406250244543686, "ce": 4.555205345153809, "genuineness": 4.419482707977295, "identity": 0.44732317328453064, "hypothesis": "Ah, he encontrado la cajita. Estaba junto a la ventana. Vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5fb543c200d4b5e77964b95f7f6b36d112be49a6bfd5ec9b206f4f2582c6d011.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "5fcfd69bd1db52ea884e3d9554257b2371063d1784760bb44589ea7edfc133ca", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02c7c24f3d65b1fade28b491de74107ccf66c84c45e8ea693fd8377fae138227", "generation_seconds_batch": 15.261345595936291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9207024574279785, "target_z": 1.1796874491969103, "ce": 5.784333229064941, "genuineness": 4.432034492492676, "identity": 0.5890522003173828, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5fcfd69bd1db52ea884e3d9554257b2371063d1784760bb44589ea7edfc133ca.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "5fd179cfdc8d3bbab846d67544462a4af6dbc47c5992586a06eab8ca0dc8d835", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b4feab8973db74cab8edebae3221afbe9cd1e660ec1d9f326fc895f48ca86f7", "generation_seconds_batch": 21.486868373933248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.109206199645996, "genuineness": 4.632867813110352, "identity": 0.5962151288986206, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/5fd179cfdc8d3bbab846d67544462a4af6dbc47c5992586a06eab8ca0dc8d835.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "60c704f61b51b3b2c231dad4594f209c78d1a4cf31d073ee2f41231052024358", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8f45aa6522b78f4e0126ab4aa39da58c34160f966f201eb1efc51036e9c7cab", "generation_seconds_batch": 21.134925603982992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487090587615967, "target_z": 4.375000234210854, "ce": 5.210475444793701, "genuineness": 4.570107460021973, "identity": 0.40137019753456116, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/60c704f61b51b3b2c231dad4594f209c78d1a4cf31d073ee2f41231052024358.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "61363d5f45f3caa4fc537a755804a2fea925f81385d6bcfb5de67d8cbec08738", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2074191d95dda8eed0f2bf93c6656d933e6681f3b57fb3af46b80231486ebe79", "generation_seconds_batch": 22.377174483030103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 5.967014789581299, "genuineness": 4.319066047668457, "identity": 0.6572793126106262, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/61363d5f45f3caa4fc537a755804a2fea925f81385d6bcfb5de67d8cbec08738.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "613dd38d28818bcb9bf5b465b4ac97135956af4ba77f656c114a35e08ae064d3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5f6a173170ee7e470d352fe49a39af44d5c3d68dabb0fbfec290e6f8211af3f", "generation_seconds_batch": 23.651916248025373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124814510345459, "target_z": 3.406249913893068, "ce": 5.22636079788208, "genuineness": 4.607763767242432, "identity": 0.8262696862220764, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/613dd38d28818bcb9bf5b465b4ac97135956af4ba77f656c114a35e08ae064d3.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "629118a535348ee2cbeb6eabcbb97beb0b6994bc11350cdf37019961ab7ec251", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a04a8a7f7a47fc071e891c0d5c9c5a7ce13f94e89f4c6faf4e0ba0c880acbd62", "generation_seconds_batch": 23.63110160792712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2544739246368408, "target_z": 1.796875043053466, "ce": 5.279973983764648, "genuineness": 4.607763767242432, "identity": 0.6693811416625977, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/629118a535348ee2cbeb6eabcbb97beb0b6994bc11350cdf37019961ab7ec251.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "629b17a2eb750f7fc4876a294b8a61b15f99c5d6bd2455cf5172c1ff136d86d3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "436729d638cdd3d74c5028bde47ed6ff3ae9f87cf92598d532533f74a37725c8", "generation_seconds_batch": 21.618246876983903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5953810214996338, "target_z": 0.5781250809405158, "ce": 6.078212261199951, "genuineness": 4.645420074462891, "identity": 0.632342517375946, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/629b17a2eb750f7fc4876a294b8a61b15f99c5d6bd2455cf5172c1ff136d86d3.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "6452a5034b60cdcf3b05fe19e93b94aa762251a914ca66d8ab86603f2f1b3917", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c18c9fba2efc0743a4d7f69da5dbcd1fdadbfda8cab8b9dcf722ae1ce3b8671", "generation_seconds_batch": 19.926106580067426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34980547428131104, "target_z": 0.12402340962288085, "ce": 5.744620323181152, "genuineness": 4.482243061065674, "identity": 0.45158910751342773, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6452a5034b60cdcf3b05fe19e93b94aa762251a914ca66d8ab86603f2f1b3917.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "64e8c7fa96846924d060922e5ef61a468785519dbb287321a8e44d70362617f4", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f43c34c851333742ca2b4a9b72723f24624671f5ceca57156dc1470b8de8ae18", "generation_seconds_batch": 16.177512650960125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4205615520477295, "target_z": 3.9531253151513703, "ce": 5.847874641418457, "genuineness": 4.595211505889893, "identity": 0.5833434462547302, "hypothesis": "Einer, deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/64e8c7fa96846924d060922e5ef61a468785519dbb287321a8e44d70362617f4.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "66398a28d472009d9ba35753f7e25a9e3792cb671682349146e13ee3a7f59d00", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0389ee604f580f69ffd58604f798249a47c1204d7bb47493cdfdb6348cbdeb11", "generation_seconds_batch": 15.735806331038475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9330952167510986, "target_z": 6.7500001377710905, "ce": 5.974957466125488, "genuineness": 4.833701133728027, "identity": 0.6660118699073792, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/66398a28d472009d9ba35753f7e25a9e3792cb671682349146e13ee3a7f59d00.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "66617f47e06e3d1881978b66a7ad47271b2cb90734c6cd3879a9fcf168df5843", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4d39cab2f8b3cf7e5197f53c43f1e342aa27eaae00fb4f64875a3cbd637ec16", "generation_seconds_batch": 22.699212047969922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3276124000549316, "target_z": 3.78125003788705, "ce": 5.617537498474121, "genuineness": 4.796044826507568, "identity": 0.7610162496566772, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/66617f47e06e3d1881978b66a7ad47271b2cb90734c6cd3879a9fcf168df5843.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "66a8caa8a9d034e35966472a82ffd85f325e36055ffa969f363a273b11a1c979", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "40c17f4bea48bc07c377ef0d889582965bba028b0dba3638d9f6a2cd7666ec45", "generation_seconds_batch": 21.329384471988305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.459900379180908, "target_z": 5.87500028931929, "ce": 5.403085231781006, "genuineness": 4.607763767242432, "identity": 0.5967952013015747, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/66a8caa8a9d034e35966472a82ffd85f325e36055ffa969f363a273b11a1c979.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "66f81f140989502b9eeaeea81faacb5724251948d4abf90d2ecd33cd162f8c9f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3acfc10bef1de7b70d8887afad3a2e364f311b11581f6b3f4223923c6863069d", "generation_seconds_batch": 21.801862300024368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5586705207824707, "target_z": 2.359374788176948, "ce": 5.974957466125488, "genuineness": 4.6956281661987305, "identity": 0.5686805248260498, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/66f81f140989502b9eeaeea81faacb5724251948d4abf90d2ecd33cd162f8c9f.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "6788be4813ac96a6a773def570cfb79da59a5529e3e5c7906540d15caf3cf810", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4889b18ed5a9401cd759a8f2af736521f1b0395102544e96bf7ec8c025f5946", "generation_seconds_batch": 19.67727264703717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 6.1894097328186035, "genuineness": 4.406930446624756, "identity": 0.3081580698490143, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6788be4813ac96a6a773def570cfb79da59a5529e3e5c7906540d15caf3cf810.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "67f17aead96e2a916128bcbf55f70fe23d793daa671f8d0df142048e2169753a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c21d7bc466ba29483913a9665fad21aecaaa7aa94e7d44d06eea2b1b2bef53d2", "generation_seconds_batch": 15.7739575849846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4768002033233643, "target_z": 5.906250299652123, "ce": 5.510311126708984, "genuineness": 4.545003414154053, "identity": 0.5489411354064941, "hypothesis": "She troubled the petite boat Elité Boite Elite Pred la vieille fenêtre.", "wer": 0.7894736842105263, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/67f17aead96e2a916128bcbf55f70fe23d793daa671f8d0df142048e2169753a.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "681e50de1c5b9dacefff886d7ac36eb639f461b6ad959126c5fee2dee335773d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5ecfc1edd1cfbbe1fbd39f17f504fc57c5fa034e3efab9eb255f5006d226e13", "generation_seconds_batch": 22.881740545039065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.608055830001831, "target_z": 0.601562478473267, "ce": 6.260893821716309, "genuineness": 4.419482707977295, "identity": 0.039699167013168335, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/681e50de1c5b9dacefff886d7ac36eb639f461b6ad959126c5fee2dee335773d.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "6826bc19116f03b220af8654de3cbd812af1432a32117f8eff1c9d8d875dcd18", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f773fe8f9897d5ed5d1cd5ff0eee3159fbfbe3e75269114d179eace0be7bdce", "generation_seconds_batch": 22.90531655610539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0981504917144775, "target_z": 1.507812337257899, "ce": 6.125868320465088, "genuineness": 4.545003414154053, "identity": 0.5751181244850159, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6826bc19116f03b220af8654de3cbd812af1432a32117f8eff1c9d8d875dcd18.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "685016d6cf4687639dee8d2650fb669bf06e843af2f2b60fed069afcd1182d6d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "84e7c47f2c674425a5f10be22e0995ce305f74af7bbb4ff953744575a704c40d", "generation_seconds_batch": 21.539545393083245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9022061824798584, "target_z": 4.843749948335841, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.679231584072113, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/685016d6cf4687639dee8d2650fb669bf06e843af2f2b60fed069afcd1182d6d.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "68a6cf70d74556dbfec9fde0784543699208b94c9a18b8569d41e5084ca42c9e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d76c8298857b49dcf4e964b6cdf7f27bae671ff57d6414998fe6e34ea651af0", "generation_seconds_batch": 21.268063241033815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3558728694915771, "target_z": 1.9843751050504568, "ce": 4.941417694091797, "genuineness": 4.168440818786621, "identity": 0.4535674452781677, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi à quand tu aurais un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/68a6cf70d74556dbfec9fde0784543699208b94c9a18b8569d41e5084ca42c9e.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "68b02ab6f7cd0eb8ebd2c3cb99529a31c7472cf15f062c3453e7faf84604e18e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac3cc32f37fa7eb991cf2fa16de0a3996543273c223b012a791fd01218457338", "generation_seconds_batch": 20.34587400802411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6938691139221191, "target_z": 2.6093748708396025, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.7312120199203491, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/68b02ab6f7cd0eb8ebd2c3cb99529a31c7472cf15f062c3453e7faf84604e18e.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "690e316698a671a0af039d79163d7fcd743173641709ebe725ee6244d7d06424", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea46c19517019d556fa03c82a115b32099575e83a8ce2919dfbc629edf317205", "generation_seconds_batch": 21.539545393083245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071204423904419, "target_z": 5.156250051664159, "ce": 5.927301406860352, "genuineness": 4.413206577301025, "identity": 0.38529807329177856, "hypothesis": "Ik heb een kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/690e316698a671a0af039d79163d7fcd743173641709ebe725ee6244d7d06424.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "69586cb77a720d9df881005104211a3235dea07a9b969394fed94830ca058015", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d982a14280b629d7578debf146f9a7792215f560f4767712bbc439b41eb1061", "generation_seconds_batch": 15.650484358076937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1488499641418457, "target_z": 1.6015623682563944, "ce": 6.086154937744141, "genuineness": 4.934117794036865, "identity": 0.7944672107696533, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/69586cb77a720d9df881005104211a3235dea07a9b969394fed94830ca058015.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "69749644a023a3eee527adbfe8adffb3043ebdb323f69a3da75125d9597be75d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1eebd69cd7e14c4532f14713086ca24528d751a9d022b57a86485935eb37bc2e", "generation_seconds_batch": 22.13861166697461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6178200244903564, "target_z": 2.4687500447756046, "ce": 5.927301406860352, "genuineness": 4.582659721374512, "identity": 0.3249179720878601, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/69749644a023a3eee527adbfe8adffb3043ebdb323f69a3da75125d9597be75d.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "697a2e0869898ddf9675b8f25ef1b5cbb8c06e930e1ceaebbb100420b2325335", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd2d005814a39143c77d7ab8e760d8aa7159847d48d949c4e5754e88816cfd66", "generation_seconds_batch": 20.6443191539729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7445685863494873, "target_z": 2.703124901838098, "ce": 5.756534099578857, "genuineness": 4.796044826507568, "identity": 0.8309268951416016, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/697a2e0869898ddf9675b8f25ef1b5cbb8c06e930e1ceaebbb100420b2325335.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "69dd16f0405b4c71741b9263bda3518a8070305f214008dd9b82dd129e435b08", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cab3850b44b3839f072953e1f85db1f3d648f82bab386e32c9aeb4bdefda7a5", "generation_seconds_batch": 22.93379846296739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6355180740356445, "target_z": 0.6523438003725551, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.7045518159866333, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/69dd16f0405b4c71741b9263bda3518a8070305f214008dd9b82dd129e435b08.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "69f6e7b8609c9c1c96a3e170b2807c0d1cef1979dcc594cad98684bd7ee49cfa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4af68501bd5a1f978662fab5ba8447afe6b53399f95842033b6ba7f792a124d6", "generation_seconds_batch": 22.185893254936673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3276124000549316, "target_z": 3.78125003788705, "ce": 5.847874641418457, "genuineness": 4.770940780639648, "identity": 0.6928850412368774, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/69f6e7b8609c9c1c96a3e170b2807c0d1cef1979dcc594cad98684bd7ee49cfa.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "6a25b84baf0d67205cdb4e452fd08270b8e48870f5c85c426b2c8006205f28ea", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4650bc5551491575411875a7def931fbd801494859a6da7e958b0aff2c9d0692", "generation_seconds_batch": 14.964853657991625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966670036315918, "target_z": 2.9843749948335843, "ce": 6.0305562019348145, "genuineness": 4.457139015197754, "identity": 0.26444604992866516, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6a25b84baf0d67205cdb4e452fd08270b8e48870f5c85c426b2c8006205f28ea.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8727f2cda90b0b087b9a448b12a2f7c4bcd439d955b4525ff8cb1fd05b615fc0", "generation_seconds_batch": 17.000126819009893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07359908521175385, "target_z": -0.38671874009770285, "ce": 6.395919322967529, "genuineness": 4.143336772918701, "identity": 0.25684404373168945, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "6ac10f3261991997386f52ad6a96be1b4e626cbf6c0a406d1075844c1c17480e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae860de626c59ba811b2d5bd26b2c43706a27161037527e7db48a50f3defea40", "generation_seconds_batch": 15.505738607957028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5304102897644043, "target_z": 4.156250161881031, "ce": 6.038498878479004, "genuineness": 4.595211505889893, "identity": 0.33820879459381104, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6ac10f3261991997386f52ad6a96be1b4e626cbf6c0a406d1075844c1c17480e.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "6adb26e37bc6acfb20c03b7056c5a14322174db0e129bf301399ccc9acf63125", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d622ba869b88b870ac02d55bdfa3a93f5f6d994dbaa3f8a792b0058785f805b3", "generation_seconds_batch": 14.269536664010957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8882172107696533, "target_z": 2.9687502101009136, "ce": 5.689021587371826, "genuineness": 4.281409740447998, "identity": 0.36653265357017517, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Pull me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6adb26e37bc6acfb20c03b7056c5a14322174db0e129bf301399ccc9acf63125.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "6b444280662307f2257c11f87cc2d3278dad7ced268ef0a0201620af5d260148", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78ec6bc5622bbaf959aa225d085913607c947a80ae8048bd59f0fa3a56d07d1d", "generation_seconds_batch": 22.338222955004312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2967233657836914, "target_z": 1.8749998484518002, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.5209928750991821, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6b444280662307f2257c11f87cc2d3278dad7ced268ef0a0201620af5d260148.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4bd228c779f6413c951fd53d99027daa4c4069a7e25c4c43c3aeb246a19e413f", "generation_seconds_batch": 13.482298107002862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48553216457366943, "target_z": 0.37500001377710906, "ce": 6.141753673553467, "genuineness": 4.6705241203308105, "identity": 0.7027958631515503, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "6bf06fdcc4c0914ae35ab749469c5bd8992e2feb20ce3276e0fe693533925fcf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "339ce9230c19de8e7a311c2d39c27a264310cf83b08e4c3d0ddb6608e5fb880c", "generation_seconds_batch": 19.87447129993234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3516478538513184, "target_z": 1.9765624922503762, "ce": 5.871703147888184, "genuineness": 4.519899368286133, "identity": 0.39680400490760803, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6bf06fdcc4c0914ae35ab749469c5bd8992e2feb20ce3276e0fe693533925fcf.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "6c0bab36575f6d205cc74d898ae5f2b4d6274f3704a93d1dbe4eb7458f36681f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "097a09f46d1d09a75cd58e30788c7f851b9455162f2f7018b4bb5c4e4195c673", "generation_seconds_batch": 15.872356152976863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.037404775619507, "target_z": 5.093750030998495, "ce": 5.315715789794922, "genuineness": 4.595211505889893, "identity": 0.7012168169021606, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6c0bab36575f6d205cc74d898ae5f2b4d6274f3704a93d1dbe4eb7458f36681f.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "6c1f6546c7a8f2c69fedfa52b77f3288e1c1d518baf7ef6bbe0fcc2a0794b3f3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "979754c6e6f58e6cb2ba2eedd09fce7572a241708a1c9140da267d314fc19572", "generation_seconds_batch": 15.234916668967344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8853063583374023, "target_z": 4.812499938003009, "ce": 5.359400749206543, "genuineness": 4.557555198669434, "identity": 0.6088950634002686, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6c1f6546c7a8f2c69fedfa52b77f3288e1c1d518baf7ef6bbe0fcc2a0794b3f3.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "6c3d18f984cddeca45e70c82feb4f7e5c0344c6a6e93a7de07dd959e724fd4e9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c9ae87a6e1d1f6bba6b9a3493d34c5fe577f6286ce9c65037bf033d35cd2ccd", "generation_seconds_batch": 22.98461381997913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5781989097595215, "target_z": 6.093749920781622, "ce": 5.266074180603027, "genuineness": 4.005263805389404, "identity": 0.11347031593322754, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht een andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6c3d18f984cddeca45e70c82feb4f7e5c0344c6a6e93a7de07dd959e724fd4e9.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "6c4d3ed29ed0a8e59bf03fcc09aded81106a6f11f80056126b3f9ccbcffee4aa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "331630d8edf56a828a1bbdd381fa4adc25d08955b0fadb885fba7ecb09926b84", "generation_seconds_batch": 20.91891167103313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1895031929016113, "target_z": 5.375000123993981, "ce": 5.260117053985596, "genuineness": 4.331617832183838, "identity": 0.6992144584655762, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6c4d3ed29ed0a8e59bf03fcc09aded81106a6f11f80056126b3f9ccbcffee4aa.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "6cc6e6833b0c41fa25e28fb9b3a3bbdd7cff5690a9abcfcf527965ee3573def1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be840d2c81cbebfac814bc622e395cf1010c1dd665f0ba5bbd75e9f3952a178c", "generation_seconds_batch": 22.14439023693558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15228885412216187, "target_z": -0.24121094837100013, "ce": 6.24500846862793, "genuineness": 4.607763767242432, "identity": 0.42309674620628357, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6cc6e6833b0c41fa25e28fb9b3a3bbdd7cff5690a9abcfcf527965ee3573def1.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "6ced2570f4e78abca0fb49a3ae34cca85426214b3212ffd16704c1aea367d492", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc21d03c1828e68b85f509078e23eed8e3e237c36741b4bb643bed73345249ea", "generation_seconds_batch": 20.44599387201015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9330952167510986, "target_z": 6.7500001377710905, "ce": 5.08339262008667, "genuineness": 4.20609712600708, "identity": 0.5639415979385376, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6ced2570f4e78abca0fb49a3ae34cca85426214b3212ffd16704c1aea367d492.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "6d44fd94963620d229d23951f0d15827bf5963df5a352e1083a976fd7d0934b5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4642fbb34af99bf3bd492310a2eb8e8498f091236e308894e71d8a0960c93329", "generation_seconds_batch": 15.4280356799718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 5.569881439208984, "genuineness": 4.808597087860107, "identity": 0.8226304054260254, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6d44fd94963620d229d23951f0d15827bf5963df5a352e1083a976fd7d0934b5.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "6d6633b559cf3192dc19047593ef62508f9374b94d4d80e8fd51a75c664adf90", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "080b1fb5d8f51419b4832f4af1b36414ee37c8c9fbb92fa3af15202391f0c283", "generation_seconds_batch": 17.527641886030324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9867053031921387, "target_z": 5.0, "ce": 5.967014789581299, "genuineness": 4.545003414154053, "identity": 0.29271453619003296, "hypothesis": "Uh the door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6d6633b559cf3192dc19047593ef62508f9374b94d4d80e8fd51a75c664adf90.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "6daf02b44493beeb4f738836dfbfea98d1d6d8c164bd6fdd5a3af0dcc7c24215", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "589b4e37629fd4cebf72229cd7a6a4f797feea5264101a477da996f6deec75d6", "generation_seconds_batch": 20.79976037296001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6418554782867432, "target_z": 0.6640624991389307, "ce": 6.173524379730225, "genuineness": 4.3127899169921875, "identity": 0.324203222990036, "hypothesis": "The door is still open. I put your coat on a chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6daf02b44493beeb4f738836dfbfea98d1d6d8c164bd6fdd5a3af0dcc7c24215.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "6db7467a1d85b5d9d38f11b7f3933da5ab3590f57667e3c89f9e026b651a6434", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f57eca365b9ad0ce2fe8714fbbd42825e5f4ea72aa29cf8648da36dd425c4c63", "generation_seconds_batch": 16.518020329996943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.014965772628784, "target_z": 3.203125067163407, "ce": 5.71682071685791, "genuineness": 4.808597087860107, "identity": 0.8246217966079712, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6db7467a1d85b5d9d38f11b7f3933da5ab3590f57667e3c89f9e026b651a6434.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "6df0948236c29e589041ec6deda8cd0330e8a2a1049b1361c991b22af82e03f6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6e5646fec979d251fbd03398f7b180ca3d05b8657383ba215cef3731aa1a165", "generation_seconds_batch": 22.921484602964483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.780996799468994, "target_z": 6.468750044775605, "ce": 5.3792572021484375, "genuineness": 4.2751336097717285, "identity": 0.31987565755844116, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6df0948236c29e589041ec6deda8cd0330e8a2a1049b1361c991b22af82e03f6.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "6e46ac2fdb6a5e69c244f3e9c07efa05f80b870eee61937b4c337ac1d5555fae", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b1bc672e874d672c685495bf6540165f4279cdf491854053c43f59669b7bfe6", "generation_seconds_batch": 16.80797480500769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.720792293548584, "genuineness": 4.482243061065674, "identity": 0.2151898443698883, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6e46ac2fdb6a5e69c244f3e9c07efa05f80b870eee61937b4c337ac1d5555fae.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "6e524bcd87c116e9c1e49acc85eb1cf7f90effc0a66df0ed0ec7edd1536555e9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc2fe24a9d038b02494829f719f6c9ea8c7430f1566c5c3a4076ccbb24ffecaf", "generation_seconds_batch": 21.35679309500847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.817707061767578, "target_z": 4.687499896671682, "ce": 5.478540420532227, "genuineness": 4.168440818786621, "identity": 0.21134495735168457, "hypothesis": "De sleutels liggen op de keukentafel. Ik in de la en daarna naast het ramen. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6e524bcd87c116e9c1e49acc85eb1cf7f90effc0a66df0ed0ec7edd1536555e9.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "6f83f04b5f403148a41112beaa4c164d7eb475254beae17af664eee23531fe8b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "82738e4feebc5c12d1011e647f6e6f6aba2bb522e0320a269482d2655f4fd0c4", "generation_seconds_batch": 22.818801123998128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5274996757507324, "target_z": 6.000000330650618, "ce": 5.343515396118164, "genuineness": 4.068024158477783, "identity": 0.030679021030664444, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6f83f04b5f403148a41112beaa4c164d7eb475254beae17af664eee23531fe8b.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "6fa365d376c1abc7fd050f72b88cda23ff8e2d9d35e51173f21268df9e81095a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a4d47f721d7a2889ce28e8f29cde49e8518b5ecbc7e075996edb0bbf0149bed1", "generation_seconds_batch": 22.943622312974185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9164775013923645, "target_z": 1.1718749466137024, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.24708428978919983, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6fa365d376c1abc7fd050f72b88cda23ff8e2d9d35e51173f21268df9e81095a.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "6fa8ddca293e6ec8f1455f6ac26977737b26f712bad5be6acb03d77a925bc75c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0426eb70d91be769dfa6097a449b6e6e855a0dc09ebdb0ad2136978f7d53d3a", "generation_seconds_batch": 21.219401914044283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2605533301830292, "target_z": -0.04101561100762359, "ce": 6.157639026641846, "genuineness": 4.808597087860107, "identity": 0.8761129379272461, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient et", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/6fa8ddca293e6ec8f1455f6ac26977737b26f712bad5be6acb03d77a925bc75c.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "7136dfe2aa6c3c1e53d60f8fcb592ed9af944bc3476df52f03b895d7c7a1ca01", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "746c660bb13324e55b0d25fc47d25de800aa40031a56980956a9a3b339744429", "generation_seconds_batch": 20.65303165500518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.341601610183716, "target_z": 5.656250216989468, "ce": 5.6254801750183105, "genuineness": 4.494794845581055, "identity": 0.8095000982284546, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7136dfe2aa6c3c1e53d60f8fcb592ed9af944bc3476df52f03b895d7c7a1ca01.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "720164f984fd10d9b82e8d3c39f4510e6165fc9ed4e9b91f5d042b9c1e50401d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e6364ecefc023d415a29501b7c2eacf8e864e22f80fa6baafdf03a76b5731c1", "generation_seconds_batch": 21.268063241033815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.817707061767578, "target_z": 4.687499896671682, "ce": 5.307773113250732, "genuineness": 4.507347106933594, "identity": 0.8418337106704712, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, les p... le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/720164f984fd10d9b82e8d3c39f4510e6165fc9ed4e9b91f5d042b9c1e50401d.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "7221e890bc03432ed0b842b9011feaae20f317de1a0f71f2708b5f15c5d6475a", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a5890b3b7aebadca4c1ffc7cf4a7c49770bbb1a78e1d47f8650feb84f1afb99", "generation_seconds_batch": 21.803113210015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750108003616333, "target_z": 4.562500296207845, "ce": 5.411027908325195, "genuineness": 4.300237655639648, "identity": 0.5609106421470642, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. How me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7221e890bc03432ed0b842b9011feaae20f317de1a0f71f2708b5f15c5d6475a.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "7225b62ad5b2fe840b40f73096435eb21a5fc20595f1770f8e55598501dd3e85", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d1c50331a55c32ece4de8911dcc80e0054c79bf6ff22e8f77754322fd4fd33c", "generation_seconds_batch": 20.280788411037065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8316962718963623, "target_z": 6.5625000757741, "ce": 5.182676315307617, "genuineness": 4.457139015197754, "identity": 0.527362048625946, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7225b62ad5b2fe840b40f73096435eb21a5fc20595f1770f8e55598501dd3e85.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "728f3159ad732b6c13563d8995f234131a16bee1acff2612b98b4e798fa2d5f7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8d36a940c520deeeca147882ad4aa44cf1c6df559a57ed1ce57bd05a8c0128b", "generation_seconds_batch": 20.503217136953026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23361924290657043, "target_z": -0.09082030119846521, "ce": 6.229123115539551, "genuineness": 4.6705241203308105, "identity": 0.20457540452480316, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/728f3159ad732b6c13563d8995f234131a16bee1acff2612b98b4e798fa2d5f7.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "729be4311ee02676c32e007f919c02fbdd333b19a2200f52b2a8c260e6071484", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dda4535420f34f959a059e3d590e1da4573eb5e1794089dfd2f1d0109284da12", "generation_seconds_batch": 23.511925903032534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.808161735534668, "genuineness": 4.457139015197754, "identity": 0.49971306324005127, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/729be4311ee02676c32e007f919c02fbdd333b19a2200f52b2a8c260e6071484.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "72b5c8dbd25e4ecc76f7de3edfc446e9f5160bdcfb4d3df5c6082843375e5685", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fe57127252e460a26a7c7f4029a77ae514b2c3b2b5c3cf640e7e04c398d8e17", "generation_seconds_batch": 15.250085219042376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8797671794891357, "target_z": 2.9531249845007523, "ce": 6.197352409362793, "genuineness": 4.6705241203308105, "identity": 0.7011324167251587, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/72b5c8dbd25e4ecc76f7de3edfc446e9f5160bdcfb4d3df5c6082843375e5685.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "72b809b4008f69e8b5afd4d50d58db6cab730e9034a369f3168971a8928f4adb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2114a835533c7f2c99b412db01c3e461ee6ec6d9b653fa4c64d32197a4559fc8", "generation_seconds_batch": 21.029559709015302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5573563575744629, "target_z": 0.5078124474747716, "ce": 5.744620323181152, "genuineness": 4.118232727050781, "identity": 0.5052964687347412, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/72b809b4008f69e8b5afd4d50d58db6cab730e9034a369f3168971a8928f4adb.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "72f9aba82219194a7faaf1daf3369f7c3e578fd69e41cfbf5058b6f438c0b203", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35a6b1473f68373829eccb9a7d39cc7905d1d8d9003eccf615add62b771b69e0", "generation_seconds_batch": 22.628989787888713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124814510345459, "target_z": 3.406249913893068, "ce": 5.879645347595215, "genuineness": 4.469690799713135, "identity": 0.5729416608810425, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/72f9aba82219194a7faaf1daf3369f7c3e578fd69e41cfbf5058b6f438c0b203.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "735a9f8662edb340438914236affe9c30ca7bfd51fea9b788d1ad1ca742afaf1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55d8f632406bfc6db43cad436653a5eab4de00e3669b8e344148b2e5d115f6d7", "generation_seconds_batch": 23.73468866501935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5473101139068604, "target_z": 4.187500172213864, "ce": 5.371314525604248, "genuineness": 4.68307638168335, "identity": 0.5328670740127563, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/735a9f8662edb340438914236affe9c30ca7bfd51fea9b788d1ad1ca742afaf1.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "7579152c860c8c5d9ae7f14f5d766f5b1e0e0eda7baa91a543d48ef5a1667e0c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72237859b6fcf8d49449f1320dd755275a3dd6481a7b69358bcd879bfea6d6e1", "generation_seconds_batch": 15.482449827017263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 4.918582439422607, "genuineness": 4.268857479095459, "identity": 0.6131572127342224, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7579152c860c8c5d9ae7f14f5d766f5b1e0e0eda7baa91a543d48ef5a1667e0c.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "75d6ebd22e9776515c40e020a20633de6eb84e025a650a63022ef4e3490e8db3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "906561b27cd7606d3e47a77c4774470751d9f1b4a29ed5323db8ca8275409f1d", "generation_seconds_batch": 25.474087564041838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7530186176300049, "target_z": 2.718750127438259, "ce": 6.109982967376709, "genuineness": 4.821148872375488, "identity": 0.6479235887527466, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/75d6ebd22e9776515c40e020a20633de6eb84e025a650a63022ef4e3490e8db3.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "75dcee4bdfbb8342da5628fdc25ffbb32437b9a7a6c1b0f198db8c5ee6c3a981", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69d854f125d923a1599857d47bf271dd063612301a2f03e7703150490834ef01", "generation_seconds_batch": 16.987118953024037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7107689380645752, "target_z": 2.640624881172434, "ce": 5.974957466125488, "genuineness": 4.758388519287109, "identity": 0.6951543688774109, "hypothesis": "J'ai j'ai trouvé la petite boîte elle était près de la billeuil et fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/75dcee4bdfbb8342da5628fdc25ffbb32437b9a7a6c1b0f198db8c5ee6c3a981.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "7603dff0c692ccc783e20b4708efe23c4d3dbfdddd44b9bbe0a4751e8b9f8052", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "add3e773910be2e67e57dd1790b2fd066e347ce622fa2747e7f9e1ff16540d7c", "generation_seconds_batch": 21.296912563033402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7052297592163086, "target_z": 0.7812499276701773, "ce": 6.086154937744141, "genuineness": 4.419482707977295, "identity": 0.40421098470687866, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7603dff0c692ccc783e20b4708efe23c4d3dbfdddd44b9bbe0a4751e8b9f8052.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "76e86480779ccfc62fd4d2d32a226527a1957be7aded91f66c617ee5b2b2bb6c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d9d5911fa35b550c70197118bfea051cc5153214a337baaf005fda67cf1b443", "generation_seconds_batch": 20.77117625705432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5642099380493164, "target_z": 4.218750182546695, "ce": 5.673136234283447, "genuineness": 4.469690799713135, "identity": 0.4077008366584778, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/76e86480779ccfc62fd4d2d32a226527a1957be7aded91f66c617ee5b2b2bb6c.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "778411e18ac99cf4d96a7bdf31f258754e06ffc76380b8008a4c10c84be632cf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64670ed81f35692217935ea91965cb340ba5b45c4997725ff3ad889691e04560", "generation_seconds_batch": 21.329384471988305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5950987339019775, "target_z": 6.124999931114455, "ce": 5.760505676269531, "genuineness": 4.557555198669434, "identity": 0.6178481578826904, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/778411e18ac99cf4d96a7bdf31f258754e06ffc76380b8008a4c10c84be632cf.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f82e6befe57dc88de2ff55324bbcf9544e00ee68e86b6db74d0f3ce5fe1dfb97", "generation_seconds_batch": 16.38133458804805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12429854273796082, "target_z": -0.2929687366534256, "ce": 6.181467056274414, "genuineness": 4.68307638168335, "identity": 0.8515626788139343, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "779b861f5c6c5076966870c6dfdb03e11b0c3a4ddf69cc7bff2926d390d736e9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01b973c9fcc22368f55f2c783b36bfe994c4e2b0e552e87ab57e7f024b529b92", "generation_seconds_batch": 21.22280247102026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3009483814239502, "target_z": 1.8828124612518806, "ce": 6.09409761428833, "genuineness": 4.7081804275512695, "identity": 0.7463457584381104, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/779b861f5c6c5076966870c6dfdb03e11b0c3a4ddf69cc7bff2926d390d736e9.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "779d1ec8227324c8bf60818c2f19355e42b056661a8a94ee6b1a04ff23d8198a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96000daf2f1eb90061d7e2cfab512de2a9f1af6fca1abfae83504ef2087b9048", "generation_seconds_batch": 21.241071246913634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8684065341949463, "target_z": 4.781249927670177, "ce": 5.816103935241699, "genuineness": 4.758388519287109, "identity": 0.5450776815414429, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/779d1ec8227324c8bf60818c2f19355e42b056661a8a94ee6b1a04ff23d8198a.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "77b0ad09fa25fc5de5a76511d378ed0b5364ae50cca76c8ee3536e8cfd0390a3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5d255a803c99c49034c8098cd0ce58ad8fb2648ed6f5612e699f7728eca6c61", "generation_seconds_batch": 16.220233965897933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2262134552001953, "target_z": 3.5937499758900593, "ce": 5.661221981048584, "genuineness": 4.7834930419921875, "identity": 0.7374038696289062, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/77b0ad09fa25fc5de5a76511d378ed0b5364ae50cca76c8ee3536e8cfd0390a3.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "77d70c72d5ac5e2659b0f42b0b05e7d5d7fc24961a66a5c3f5e5095aa05140c7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a1f7dd382e3c82f442e171f4a83c36940a0a78617390b984a8370dc7fb4df2c", "generation_seconds_batch": 22.55927092989441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.769918441772461, "target_z": 2.750000137771091, "ce": 6.038498878479004, "genuineness": 4.507347106933594, "identity": 0.5362568497657776, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/77d70c72d5ac5e2659b0f42b0b05e7d5d7fc24961a66a5c3f5e5095aa05140c7.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "78174c39062e30b6eaa1b607c87bab44117a513a478cec460a616f23231be8aa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b768d5ba8844006f76fa4b65b9dbe0678949061b912f54ae9e0e39a555d9781f", "generation_seconds_batch": 22.365109030040912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.643169641494751, "target_z": 2.5156248398411067, "ce": 5.331601142883301, "genuineness": 4.7081804275512695, "identity": 0.7393558621406555, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/78174c39062e30b6eaa1b607c87bab44117a513a478cec460a616f23231be8aa.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "782dcb959a671644b8f11d158eb86eddf276c75ff9453ee992bf9b32078cfc15", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6a8154e3ce42d523b9e423063644eee00e6a432afdabc0e760e615abfe031ecf", "generation_seconds_batch": 20.901350981090218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5274996757507324, "target_z": 6.000000330650618, "ce": 5.677107334136963, "genuineness": 4.306513786315918, "identity": 0.48055681586265564, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/782dcb959a671644b8f11d158eb86eddf276c75ff9453ee992bf9b32078cfc15.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "783fda730d58498c20387264ab3a93400dcc32ec2697c192f9d1b32ab193d891", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a5500d670079fcb0ef6d6017a8e3b5665c6489a4dd138004d7a2a39841c47bb", "generation_seconds_batch": 21.44605724106077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8953527808189392, "target_z": 1.1328125439145351, "ce": 5.903473377227783, "genuineness": 4.507347106933594, "identity": 0.5633529424667358, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/783fda730d58498c20387264ab3a93400dcc32ec2697c192f9d1b32ab193d891.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "785766803cf383ea86c4c9a025c3f82c7aa307046b5092243748774b4dd59fee", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8723a292d10cf72e2e9b8415a61dc87e94c1f8a4131c81797863ee04fe7a37bd", "generation_seconds_batch": 16.6939540929161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6685194969177246, "target_z": 2.5625000757741, "ce": 5.935244083404541, "genuineness": 4.720732688903809, "identity": 0.7109272480010986, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/785766803cf383ea86c4c9a025c3f82c7aa307046b5092243748774b4dd59fee.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "78bef0304ad82b707a385166c1cc6c878f4f4d9f63e712cafe6764036c6d6b6f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8651cf940cf8b2b1de23a237f10ad33523187d2ca72b6bf8be719dd0d8416a5f", "generation_seconds_batch": 16.4895271420246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 5.065521717071533, "genuineness": 4.105680465698242, "identity": 0.3463594615459442, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/78bef0304ad82b707a385166c1cc6c878f4f4d9f63e712cafe6764036c6d6b6f.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "78d73e738cee706bd301f6c0095d5c43d651628b5a5218f9f35a0e8b9200cb19", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1bbcbe915860f0f5dc0695b31ddb12be918fcf21d15ff51cac49e93d00091da", "generation_seconds_batch": 22.13444921001792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.088104248046875, "target_z": 5.187500061996991, "ce": 5.538110733032227, "genuineness": 4.375550270080566, "identity": 0.6085965633392334, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/78d73e738cee706bd301f6c0095d5c43d651628b5a5218f9f35a0e8b9200cb19.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "78e4e93f3bba4c2a120aa3a8634934c9ebc5bcc463b076e635668cd3cf819e7b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be5a99ea8081541fd9b408425c03f056219d27c673f488ceb46be4fd759d146c", "generation_seconds_batch": 21.158034638967365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13063596189022064, "target_z": -0.2812500103328318, "ce": 6.340320587158203, "genuineness": 4.6705241203308105, "identity": 0.3323556184768677, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/78e4e93f3bba4c2a120aa3a8634934c9ebc5bcc463b076e635668cd3cf819e7b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "78ea7991b2e7dfb9d16b73ff226accb45832e30202be90daa82ed95889f6093b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9989c904eaba58cdb93425390fdc353c5030a816b56b15706777dabf9db8774b", "generation_seconds_batch": 22.365109030040912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.200863838195801, "target_z": 3.5468751808245567, "ce": 5.792276382446289, "genuineness": 4.946669578552246, "identity": 0.7450117468833923, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/78ea7991b2e7dfb9d16b73ff226accb45832e30202be90daa82ed95889f6093b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "7903e8ac2267819b55276e2a1577b424a83979c5d055a3508294fede5ba607e0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c9b641c85de169ff1bd447d1d039847db1596229468440970f99ab0ee9ad4d0", "generation_seconds_batch": 22.13887829007581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04508063197135925, "target_z": -0.4394531325343565, "ce": 6.403861999511719, "genuineness": 4.362998008728027, "identity": 0.7040181159973145, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7903e8ac2267819b55276e2a1577b424a83979c5d055a3508294fede5ba607e0.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4bab332c333a60869ec8032dba96c82ed7ca334fb09131bf11e4f493564d317", "generation_seconds_batch": 14.922703159041703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15492945909500122, "target_z": -0.2363281204793861, "ce": 6.046441555023193, "genuineness": 4.337893962860107, "identity": 0.7292214632034302, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "797b5ca30c0694fd5ad11e1480fc2f5cd6297188fa5f68e3d3ddd7575b370514", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3b75b22ec32a8c3fe7d2413ade5fd547b8c342b9ad0a61fd7a1599aee973017", "generation_seconds_batch": 15.225561915896833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6318092346191406, "target_z": 4.343750223878023, "ce": 5.474569320678711, "genuineness": 4.6956281661987305, "identity": 0.69037926197052, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lasse sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/797b5ca30c0694fd5ad11e1480fc2f5cd6297188fa5f68e3d3ddd7575b370514.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "7a2bd935978f17d080e233f26bd7cb2a273df983dad8358690f505e6a817b996", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "de8e0e394252c44f534fab2d6b52e7f06983c8be287c5fdd2a8c29c76e54fe09", "generation_seconds_batch": 21.753765398985706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9389164447784424, "target_z": 3.0624998002319184, "ce": 5.11317777633667, "genuineness": 4.557555198669434, "identity": 0.6863098740577698, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Dann leg dich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.08333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7a2bd935978f17d080e233f26bd7cb2a273df983dad8358690f505e6a817b996.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "7a335fc8d80416c335c8fa35b1e46042d6255f0080cf6674f5a7c01bf6790704", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dd92205dd8db33a005e02f56d360b8455e52a76f45218d4d4259e187e4c6487", "generation_seconds_batch": 21.278198604937643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8375177383422852, "target_z": 2.8750001791024182, "ce": 5.847874641418457, "genuineness": 4.432034492492676, "identity": 0.5504428148269653, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7a335fc8d80416c335c8fa35b1e46042d6255f0080cf6674f5a7c01bf6790704.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "7a3be69d777643b07da36d2255e79df39834b6b6307c5a2c644ef0a16f4b0a8d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d999cedfccf05cd384649582276798cfb1efc53d49354385118b4ae6eb516eb1", "generation_seconds_batch": 20.6443191539729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1332645416259766, "target_z": 3.4218751394932294, "ce": 5.895530700683594, "genuineness": 4.909013748168945, "identity": 0.6079341173171997, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7a3be69d777643b07da36d2255e79df39834b6b6307c5a2c644ef0a16f4b0a8d.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "7b463ee74abad69fed862d72159b353210599996958eb30e5460e4f846205d47", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abf6d7c30071e2a726e24565c410169e100eb1c35782b0d0a5723882d2afa6e2", "generation_seconds_batch": 17.79698585299775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9529056549072266, "target_z": 4.937499979334336, "ce": 5.426913261413574, "genuineness": 4.607763767242432, "identity": 0.6567627191543579, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai à l'autre côté.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7b463ee74abad69fed862d72159b353210599996958eb30e5460e4f846205d47.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "7b4ce0e0afe4046c90b5a95799bc3b9068939bb0ee5737def93234d9078d635c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "de6a7eb5f6cd2e1dc105c00e0eb417ef75e266bb9acc9d3cb4b0b0f285bdc90a", "generation_seconds_batch": 13.98071896203328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3535023331642151, "target_z": 0.13085939071451505, "ce": 6.38797664642334, "genuineness": 4.7332844734191895, "identity": 0.4185459017753601, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7b4ce0e0afe4046c90b5a95799bc3b9068939bb0ee5737def93234d9078d635c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "7b5694fb13d6c1d3353bfb7f272132164f7546455dadd3cd289e601dbef95a41", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "462cb7212dced02996a9b11acf66e6821d64f34370ab3c8986c51cf9383fa0d0", "generation_seconds_batch": 24.200999881024472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8797671794891357, "target_z": 2.9531249845007523, "ce": 5.272031307220459, "genuineness": 4.607763767242432, "identity": 0.5955536365509033, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7b5694fb13d6c1d3353bfb7f272132164f7546455dadd3cd289e601dbef95a41.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "7bc60b056b70207cbf7cf292725e5106c0cf5f24aa8baa278a23d1323869a763", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e8c78f7baf09cc9d0672fb17add163c0a8f1c9fb5717991439afac6cb1b35f1", "generation_seconds_batch": 15.779951466945931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2233028411865234, "target_z": 5.437500144659645, "ce": 5.557967185974121, "genuineness": 4.6956281661987305, "identity": 0.6950469613075256, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7bc60b056b70207cbf7cf292725e5106c0cf5f24aa8baa278a23d1323869a763.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "7be5ce7cf55b85d7be9283d9cbf7e2d55bb803f58fd6662252d5899c41f61342", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6470fb606f30c62bab38de19b0413a7e74225addc7605890e14666542aa5ebb2", "generation_seconds_batch": 22.214174868073314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071204423904419, "target_z": 5.156250051664159, "ce": 5.927301406860352, "genuineness": 4.406930446624756, "identity": 0.15100345015525818, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7be5ce7cf55b85d7be9283d9cbf7e2d55bb803f58fd6662252d5899c41f61342.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "7bec5fc66e3bfd5839623e8577ad3f15d00a71f0fb101e293d18e4792e1c541d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67fae1911c98f15feef2ba0eb11c49714709fef9412a9a3759eb0c0e51e8744b", "generation_seconds_batch": 21.22280247102026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6938691139221191, "target_z": 2.6093748708396025, "ce": 5.990842819213867, "genuineness": 4.645420074462891, "identity": 0.7682285308837891, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7bec5fc66e3bfd5839623e8577ad3f15d00a71f0fb101e293d18e4792e1c541d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "7c8ab7b944d82ea744a85a5ef7a48f459e70a158f764c6cf3befb2c9327a60af", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "06dfcd56b4932599192dc4c3e4d0329a22cb708212fe33e295475d21b3fb5200", "generation_seconds_batch": 21.66639742802363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4319219589233398, "target_z": 2.1249999311144547, "ce": 6.41180419921875, "genuineness": 4.8588056564331055, "identity": 0.46980395913124084, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7c8ab7b944d82ea744a85a5ef7a48f459e70a158f764c6cf3befb2c9327a60af.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "7cbcedbf5663ce4e82d76213f2698b40e769b193f7416ab0a885c10f4e5929b6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c1ac31c841504f86183cef0cbe46d3de691a9651f251bf806b8cea9fbb9897f", "generation_seconds_batch": 20.49008314392995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.499521255493164, "target_z": 2.249999972445782, "ce": 5.673136234283447, "genuineness": 4.394378662109375, "identity": 0.514275074005127, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7cbcedbf5663ce4e82d76213f2698b40e769b193f7416ab0a885c10f4e5929b6.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "7d190351a8fc6b8d1908cc770c9dacb83eb5ac5dc31170e526dc4685a70314b2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0474f289da7d07b0d3b8f8e9a59574bf78f53daf972036bc29bbd3003b550fa0", "generation_seconds_batch": 20.991344004985876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2233028411865234, "target_z": 5.437500144659645, "ce": 5.323658466339111, "genuineness": 4.6203155517578125, "identity": 0.5457261800765991, "hypothesis": "Alguien ha movido una pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7d190351a8fc6b8d1908cc770c9dacb83eb5ac5dc31170e526dc4685a70314b2.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "7d1f695c09c72159fd05c831c7a983e72add5d9a9b1aca14f7ffa2ff80e2d2cb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce8a2485866cd504bea62c6742a781094bc70199b2c50e08fe78f58390eea804", "generation_seconds_batch": 21.269782681949437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124814510345459, "target_z": 3.406249913893068, "ce": 5.486483573913574, "genuineness": 4.821148872375488, "identity": 0.6409153938293457, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7d1f695c09c72159fd05c831c7a983e72add5d9a9b1aca14f7ffa2ff80e2d2cb.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "7dc6b3713943a6d86e6896d62f6692512875e3f85e5963ae46255ddd30b4869b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "172d8b69cd60eab033052ea6f8edc4f23d16c730782306f062661eb07bf6ac65", "generation_seconds_batch": 15.83741216501221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.000694274902344, "target_z": 6.874999738234927, "ce": 5.506340026855469, "genuineness": 4.545003414154053, "identity": 0.550553023815155, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7dc6b3713943a6d86e6896d62f6692512875e3f85e5963ae46255ddd30b4869b.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "7e92b374d458aa176a453b435a239015f8a1a7e7fa0adbb820e52b138172b596", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c25cf85f038ed3885b25beeba13dce2a39b6f331a23830db0681c4c3284251bc", "generation_seconds_batch": 19.709864542004652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.305173397064209, "target_z": 1.8906250740519612, "ce": 5.71682071685791, "genuineness": 4.545003414154053, "identity": 0.4657640755176544, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7e92b374d458aa176a453b435a239015f8a1a7e7fa0adbb820e52b138172b596.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "7eb3c5d8954808d08634fc7d62982b9b424c2ef11a2d266104f53922cdd44725", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2215b801cccd23e381c695bc1d63cf4c63cfc09b5d27dfa765f2cb11c027fac4", "generation_seconds_batch": 16.184819745016284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4234721660614014, "target_z": 2.109375146381784, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.41404497623443604, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7eb3c5d8954808d08634fc7d62982b9b424c2ef11a2d266104f53922cdd44725.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd41253763a1bd3bb64a0a81608cacb9ddce226147385443368623fd3238b33a", "generation_seconds_batch": 15.012961250031367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12641100585460663, "target_z": -0.28906251291603974, "ce": 6.4515180587768555, "genuineness": 4.482243061065674, "identity": 0.4784383177757263, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "7fbd935e2deac9a2f50bd35fc19dbaa5f4da40a1573483b7be1dfdefd1d064cc", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eb87524ce127815e320653d3ebb9a15d34aa3a0dd5b8e841bf21e4b4ef415a2d", "generation_seconds_batch": 22.13444921001792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 4.950353145599365, "genuineness": 4.607763767242432, "identity": 0.5796440839767456, "hypothesis": "Las llaves están en la mesa de la cocina, miren el cajón, y luego junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/7fbd935e2deac9a2f50bd35fc19dbaa5f4da40a1573483b7be1dfdefd1d064cc.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "802385f047f232b41cc92d67c726e43e723bfcb96287af19aabd5f6bd2c4244c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f30bfc62a8b37616dc98a6ac255c15c56af2d1ef6858b8760812e61e40bcfb01", "generation_seconds_batch": 15.695513668004423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.696497678756714, "target_z": 6.312499993111445, "ce": 5.530168056488037, "genuineness": 4.105680465698242, "identity": 0.2756894826889038, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/802385f047f232b41cc92d67c726e43e723bfcb96287af19aabd5f6bd2c4244c.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "80532617b238a8bc428f90d18c04a2147a7967c30a09f5f3a6baae2a474dac15", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1841bcdd7405fca363da131412420077ee6502744a4d276be7b2da7c72659616", "generation_seconds_batch": 21.278198604937643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124814510345459, "target_z": 3.406249913893068, "ce": 5.847874641418457, "genuineness": 4.055472373962402, "identity": 0.5128625631332397, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/80532617b238a8bc428f90d18c04a2147a7967c30a09f5f3a6baae2a474dac15.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "80848294b157e7ba4f5ed7722e4d03aa58ac7ade9221c4f1e14547aa36eff3f5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a94ee444bee1586ffe0bbf242ddf6254d4810c0bdf12ef4195ea102982f74bd8", "generation_seconds_batch": 16.78469371504616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 5.974957466125488, "genuineness": 4.582659721374512, "identity": 0.3462982177734375, "hypothesis": "Als je bericht kwam nadat ik vertrokken was, ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/80848294b157e7ba4f5ed7722e4d03aa58ac7ade9221c4f1e14547aa36eff3f5.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "809043461a8fe9807cfa9c73e005723e37a7a405cea44b7a01a39a82a039c108", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "285bd575eb891bbf7b473d876f56e87ccf2de0775c7a4c3235d74c1aae7ac3e5", "generation_seconds_batch": 20.898452191031538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1361751556396484, "target_z": 1.578124970723643, "ce": 6.078212261199951, "genuineness": 4.243753433227539, "identity": 0.3962056040763855, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/809043461a8fe9807cfa9c73e005723e37a7a405cea44b7a01a39a82a039c108.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "80b2feb427f21c29d09592ba760b599171e6398a33266835916212883db35ec2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18fc91619edcce7ee35d3d7fde51f0c602373324dfaf79927e94d488ff7e4f89", "generation_seconds_batch": 14.998238055966794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2262134552001953, "target_z": 3.5937499758900593, "ce": 6.054384231567383, "genuineness": 4.833701133728027, "identity": 0.755843997001648, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/80b2feb427f21c29d09592ba760b599171e6398a33266835916212883db35ec2.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3ebdf4403bee45965462b740b2a9ba36d8253df60dbc96bf29378a03fe4ead1", "generation_seconds_batch": 15.856443743105046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4506762623786926, "target_z": 0.3105468399114253, "ce": 6.149696350097656, "genuineness": 4.582659721374512, "identity": 0.5608736276626587, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "814006acf8ffbb88d948df7b2989db841768fa1ac9935b5962118fc50a10a8bb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbf7ff7c3d217588eb2ec73b3ebdb061b1f540e452e95e0e8dbd6ccdee3175be", "generation_seconds_batch": 22.26232389290817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6009202003479004, "target_z": 2.4375000344427726, "ce": 6.197352409362793, "genuineness": 4.871357440948486, "identity": 0.5740853548049927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/814006acf8ffbb88d948df7b2989db841768fa1ac9935b5962118fc50a10a8bb.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "81459bb98b2983a8e52b9a3914e02b109b6b393553c465032a10c2248a34359e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "639a8bc0e0d82a935e527685b268870088fe495890db25acd141bbfaee778587", "generation_seconds_batch": 22.97298427403439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.358501434326172, "target_z": 5.6875002273223, "ce": 5.414999485015869, "genuineness": 4.293961524963379, "identity": 0.4061264395713806, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/81459bb98b2983a8e52b9a3914e02b109b6b393553c465032a10c2248a34359e.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "816e934249419f65501fdbeb41c31f90622e3edd05148c791f59c5e15f69ec0b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2e3316f07dd573c9be077c14122e26a073584682d0a942bb6a994a5d1098095a", "generation_seconds_batch": 15.48974129196722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 5.5738525390625, "genuineness": 4.168440818786621, "identity": 0.04537495970726013, "hypothesis": "De sleutels liggen op de keukentafel. Kijk je dan. En daarna naast het raam. Neem ze mee dat je weggaat.", "wer": 0.2727272727272727, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/816e934249419f65501fdbeb41c31f90622e3edd05148c791f59c5e15f69ec0b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "81c916b3516ba699e399305a629488f8a86b6c39f216aa2b333003c84eba2497", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "44ced714a15c5289964d9a9b092225d0deecc36c991946fd5d6721aa67f50957", "generation_seconds_batch": 21.739978451048955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2909021377563477, "target_z": 5.562500185990973, "ce": 5.403085231781006, "genuineness": 4.545003414154053, "identity": 0.7360391020774841, "hypothesis": "Una puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/81c916b3516ba699e399305a629488f8a86b6c39f216aa2b333003c84eba2497.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "81f9598ae8a49c9847f71de0d054274c877ec97302f3bd1b0fc7c7e51c14c8a3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84f1d9058b0e8f4e16e6751f23d4f9b1072a4cbc927fd5e41eaff568c6f6cd33", "generation_seconds_batch": 22.669840955059044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 5.375286102294922, "genuineness": 4.68307638168335, "identity": 0.6979455947875977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/81f9598ae8a49c9847f71de0d054274c877ec97302f3bd1b0fc7c7e51c14c8a3.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "8214843cd8f93a6a2a8727615a54e779535bd96f1834d3ec8bc30d8dad574656", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "854487e127c0ff0f96d7331c582706b612e0bc652d0755da0cf41a8b619c4f19", "generation_seconds_batch": 14.7830396220088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8628673553466797, "target_z": 2.9218749741679204, "ce": 6.09409761428833, "genuineness": 4.7332844734191895, "identity": 0.8389857411384583, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8214843cd8f93a6a2a8727615a54e779535bd96f1834d3ec8bc30d8dad574656.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "82203cc478b3c3cd2e2ed3d10797a13b50b4b47bc8954f6161561ab5f81999ce", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2cb86615d166b125b1ca3439194d2837ad236d484192f106e477733b5029699", "generation_seconds_batch": 26.864096089964733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2262134552001953, "target_z": 3.5937499758900593, "ce": 5.156862258911133, "genuineness": 4.21237325668335, "identity": 0.633326530456543, "hypothesis": "The keys are on the kitchen table. I checked the drawer and looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/82203cc478b3c3cd2e2ed3d10797a13b50b4b47bc8954f6161561ab5f81999ce.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "822e94e5a41d7240934629f3c2515bfad216938e488f60752349574a1f13f3dc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02526c08de1245ee37a3c6de39647390959190499c27646770ccfed1e4d42c26", "generation_seconds_batch": 22.810742693021894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0065157413482666, "target_z": 3.1874998415632456, "ce": 6.078212261199951, "genuineness": 4.770940780639648, "identity": 0.7330765724182129, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/822e94e5a41d7240934629f3c2515bfad216938e488f60752349574a1f13f3dc.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "8240079d3856ce70e60ba1d340ffd9317e2d216b055be8be003cf297ef8eb6d6", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "23bb689f8b20ec4abeb44fda858e2a567ace3738bf095256e7ab72599745d5c8", "generation_seconds_batch": 16.855339369969442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.679597854614258, "target_z": 6.281249982778614, "ce": 5.262103080749512, "genuineness": 3.8922953605651855, "identity": 0.4980309307575226, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8240079d3856ce70e60ba1d340ffd9317e2d216b055be8be003cf297ef8eb6d6.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "82713a8de6b11691621bce3155b276c00c4877cbf3a8c0f4bc2487947a912b13", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "562235fa1f9d15c936ea1bc91d30bd16790aa4200ddb247d83e91c3331b8347c", "generation_seconds_batch": 17.55874256696552, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24999094009399414, "target_z": -0.06054686746564347, "ce": 6.165581703186035, "genuineness": 4.645420074462891, "identity": 0.6918172836303711, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/82713a8de6b11691621bce3155b276c00c4877cbf3a8c0f4bc2487947a912b13.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "82ce2e586d1c055b2e8c4d1b9b0f453ea659b760ab0fd31ee6dfae3503b98741", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50d1e4b5209bbc1d7e49bcc67426d5eef43b1eb32ba3fe6390637d414f3c785a", "generation_seconds_batch": 15.484503711923026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9191060066223145, "target_z": 4.874999958668673, "ce": 5.49045467376709, "genuineness": 4.306513786315918, "identity": 0.29318952560424805, "hypothesis": "Her message arrived after I left. I read it twice before putting the phone away. Let me know and we can talk.", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/82ce2e586d1c055b2e8c4d1b9b0f453ea659b760ab0fd31ee6dfae3503b98741.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "82f58ba65eb4484dff3b32988c2c861bf7812f1cc5341956798098097e4756f7", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4c535bbf980627f3e37165d7c795c18fb6285760535fec969e95d0ba5e4524a", "generation_seconds_batch": 22.45931399310939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.088104248046875, "target_z": 5.187500061996991, "ce": 5.871703147888184, "genuineness": 4.369274139404297, "identity": 0.43943914771080017, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone. Let me know when we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/82f58ba65eb4484dff3b32988c2c861bf7812f1cc5341956798098097e4756f7.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "8356fe801b77da47dfda141e9642d410f7e33a4f9b9603b0ca71df6b08501ba9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb9c8c2108cafe110b1d82a4989ca3cdbc870434f220afb68f95ea310d280cc4", "generation_seconds_batch": 22.86245118000079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.716308355331421, "target_z": 4.500000275542182, "ce": 5.720792293548584, "genuineness": 4.545003414154053, "identity": 0.2836821973323822, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8356fe801b77da47dfda141e9642d410f7e33a4f9b9603b0ca71df6b08501ba9.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "83bce6c080d0b422cdd538ac3e8cedb353b81f1d943367a8c674a30697efa507", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c81c8e3f7e1d3ca296366a9b9e2cd4d14940edc1cd2b7565d6a6aeb0d92b992f", "generation_seconds_batch": 20.414894553949125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6487090587615967, "target_z": 4.375000234210854, "ce": 5.95112943649292, "genuineness": 4.7081804275512695, "identity": 0.6535766124725342, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/83bce6c080d0b422cdd538ac3e8cedb353b81f1d943367a8c674a30697efa507.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "83f6df6b0fd1baa9eb1726b3ee81afa51ebce95e9ace690deacbe20f66bfc4f7", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "756faedf0776af7a872e0b6c064e53489814ad63eec426dfb05b5c23c261bc09", "generation_seconds_batch": 16.712107360945083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.834606885910034, "target_z": 4.718749907004514, "ce": 5.184661865234375, "genuineness": 4.532451152801514, "identity": 0.5782941579818726, "hypothesis": "Ton message est arrivé après mon départ, je l'ai relu, puis j'ai rangé mon téléphone. Et dis-moi quand nous pouvons parler.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/83f6df6b0fd1baa9eb1726b3ee81afa51ebce95e9ace690deacbe20f66bfc4f7.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "84d9c57d3ff4a22cdd221d491bd5e82d786504b073541e2cbb29ac1148aee9a1", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04e8cb75c090a5a7d8568f9e40fe21254d84febb6596869219e341731729da5e", "generation_seconds_batch": 16.09256077092141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.699408531188965, "target_z": 4.46875026520935, "ce": 5.00694465637207, "genuineness": 4.042920112609863, "identity": 0.6577621102333069, "hypothesis": "Lisez-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.3181818181818182, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/84d9c57d3ff4a22cdd221d491bd5e82d786504b073541e2cbb29ac1148aee9a1.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "851612fa0f9073941646ce46778b3edf3e26fd0c23286bb24ff858820e18538e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f098ce98437d3c787918deff564b73fb48d52a52d89cf13a807b127e1ecdd64", "generation_seconds_batch": 20.62316119496245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2769129276275635, "target_z": 3.6875000068885546, "ce": 5.665193557739258, "genuineness": 4.7081804275512695, "identity": 0.8568437099456787, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/851612fa0f9073941646ce46778b3edf3e26fd0c23286bb24ff858820e18538e.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "858d70eefb5a2bfa685369727b0096139dd811495a4ef29e5fa08b972e42619a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01ebe12d27e1ff40d671b2fbc2a734c90bff75c00e52a44c2e92237aeed8ad1f", "generation_seconds_batch": 21.70256960694678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.783907651901245, "target_z": 4.625000316873509, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.25622451305389404, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/858d70eefb5a2bfa685369727b0096139dd811495a4ef29e5fa08b972e42619a.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "85b4be6a5be83779533e4d3afffc548d7f0c8a4c0a63b4f1f77853c9d8a7e180", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a93feb48c6047f86dd43ece3c6c3dfd621be53396431b2f19f0ee2683164cb17", "generation_seconds_batch": 21.288332144962624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9529056549072266, "target_z": 4.937499979334336, "ce": 5.629451274871826, "genuineness": 4.632867813110352, "identity": 0.6334322690963745, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/85b4be6a5be83779533e4d3afffc548d7f0c8a4c0a63b4f1f77853c9d8a7e180.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "85eea2d3a741b771d22de5fd0fecfd68668b130e5c7ca5448660fb6b5b9c5785", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "477405677b59da57dfee9106f075ce6e3c5aea0aab28232bab1f8fa322d895ed", "generation_seconds_batch": 16.252663746941835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.034776210784912, "target_z": 1.3906249087266525, "ce": 5.990842819213867, "genuineness": 4.7834930419921875, "identity": 0.733109712600708, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/85eea2d3a741b771d22de5fd0fecfd68668b130e5c7ca5448660fb6b5b9c5785.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "861a62331a1c442692c61118139b24553d471210adcbf4e7ef5dc837320f98f8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96bc64a32d6100ae5394c6ce518a25c1fe1ee72d07b461baf8baabcd10c293ce", "generation_seconds_batch": 16.165209794067778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8290677070617676, "target_z": 2.859374953502257, "ce": 5.982900142669678, "genuineness": 4.344170093536377, "identity": 0.5681915879249573, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/861a62331a1c442692c61118139b24553d471210adcbf4e7ef5dc837320f98f8.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "864441271a922ac07978752d5734a18ed40e51e0c3392d382d3f2ebb69861f6d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dad1133c9078a9b7323e2747f629de1daceacfa2a8febe7ca79b1decaaf80f86", "generation_seconds_batch": 21.241071246913634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9135668277740479, "target_z": 3.0156250051664157, "ce": 5.700935363769531, "genuineness": 4.532451152801514, "identity": 0.7218236923217773, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/864441271a922ac07978752d5734a18ed40e51e0c3392d382d3f2ebb69861f6d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "8652cc2a8720d15eed56f05e1ac62d2df76cc24d3255035b08a25ec1c88c355a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "97ff8039d7a9d1e3ddfc284464c794f3c399057df3c6d9d33efe4d789b29ca79", "generation_seconds_batch": 22.881740545039065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22886615991592407, "target_z": -0.09960938038168324, "ce": 6.1020402908325195, "genuineness": 3.886019229888916, "identity": 0.2799175977706909, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8652cc2a8720d15eed56f05e1ac62d2df76cc24d3255035b08a25ec1c88c355a.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "8655cec0e1463b2d3e9e250990d2af2604f7a6c747f030bf1c397a1e88de6ec6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "108268215d18d28ca4f5c6568929a402136bfedc22591ae53045a6d5a3e2d878", "generation_seconds_batch": 22.579855468007736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2568565011024475, "target_z": -0.04785153699082147, "ce": 6.292664527893066, "genuineness": 4.645420074462891, "identity": 0.5105289220809937, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8655cec0e1463b2d3e9e250990d2af2604f7a6c747f030bf1c397a1e88de6ec6.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "865eacc475ca8d7038e8ba37286ff790c7d65f1c8a4a3bf8dbb5f694fdab48cb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ccd79af89fb7e8ee46579d462e918d7dc5cc70b52afdb3f9eb04b5ebb65f969", "generation_seconds_batch": 21.32508586999029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2093136310577393, "target_z": 3.5624999655572274, "ce": 5.335572719573975, "genuineness": 4.469690799713135, "identity": 0.7349735498428345, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/865eacc475ca8d7038e8ba37286ff790c7d65f1c8a4a3bf8dbb5f694fdab48cb.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "86831ebea35defd89308727883e268e0db1b8f38969be95c73f1e17936004e76", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b360ef088652e2aea694c920b3c2d2e7fd2d2babca1f6eaeb0487e999502ff5", "generation_seconds_batch": 19.08834764396306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5164210796356201, "target_z": 2.2812499827786135, "ce": 5.831989288330078, "genuineness": 4.632867813110352, "identity": 0.6801850199699402, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/86831ebea35defd89308727883e268e0db1b8f38969be95c73f1e17936004e76.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "868a46fbd0dc798504461d94acd14ed2913d5f7468c9161602711da2cde8e112", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a57ab8dbc09a5c259a228b5f45f182e2659cebee0801a62f60aef1eb7c3cdf0", "generation_seconds_batch": 15.290757515002042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7361187934875488, "target_z": 2.687500117105427, "ce": 5.919358730316162, "genuineness": 4.457139015197754, "identity": 0.6022506952285767, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/868a46fbd0dc798504461d94acd14ed2913d5f7468c9161602711da2cde8e112.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "868b1addc62bdda0188428283c489bafa1d1a77b493577e3ee4553713c178b9b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2337202b692d9aac022d4aca6b8bd58d0a5279f5cadb5fafd996009f19a7a67", "generation_seconds_batch": 20.109722063993104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7023191452026367, "target_z": 2.6250000964397637, "ce": 6.0146708488464355, "genuineness": 4.6705241203308105, "identity": 0.6175472736358643, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/868b1addc62bdda0188428283c489bafa1d1a77b493577e3ee4553713c178b9b.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "869e40c45ba19afc9ff4ce832a10dbdbfe34057b1686392f61eb40499b9a4f3c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "974cf1389606598f04154730a3b1da0744480ed9d1fed6b50c4eaf24c61007b2", "generation_seconds_batch": 25.20542045496404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 5.959072113037109, "genuineness": 4.444586753845215, "identity": 0.22802385687828064, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/869e40c45ba19afc9ff4ce832a10dbdbfe34057b1686392f61eb40499b9a4f3c.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "86bf556064b121fb4154b00fa38e509ce71a818bc5020a598e4185aeeb46cc97", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb1de090f3ffdcdb4e6c6df6af0a1120de54945d55a4add340dfb5b29c786756", "generation_seconds_batch": 22.014108513016254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5924701690673828, "target_z": 2.4218748088426114, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.4161628186702728, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/86bf556064b121fb4154b00fa38e509ce71a818bc5020a598e4185aeeb46cc97.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "86c5f47f586e35fb26cd84552b5ed824c1098af9fa5cabaef191c3ac352a4e39", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ebe3cfd68686555b7f0185e3e235775558a8592af839c1cbfc6061fc36d1df00", "generation_seconds_batch": 14.744484603055753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.94736647605896, "target_z": 3.0781250258320796, "ce": 5.137005805969238, "genuineness": 4.243753433227539, "identity": 0.6907786130905151, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/86c5f47f586e35fb26cd84552b5ed824c1098af9fa5cabaef191c3ac352a4e39.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "877c5fc1398468d1cfa7659bfbe0c20aa98bce4dbe5913b0b8276ac7bdba0d6f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa9e7d20f64570851883abafa340885a5ce84b9d6decc5b93438e93fffcca51e", "generation_seconds_batch": 22.238883596961387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1781667172908783, "target_z": -0.19335935627174233, "ce": 6.284721851348877, "genuineness": 4.3127899169921875, "identity": 0.4224030077457428, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/877c5fc1398468d1cfa7659bfbe0c20aa98bce4dbe5913b0b8276ac7bdba0d6f.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "87bbface75c795d44ea986270ed4529ecfae8d481cae911f5f521eb86a0b0aa3", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38c1f3bb17904890b160b44463d52f971256eda563d78c5e349c757f1a12eb9b", "generation_seconds_batch": 20.29275029199198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0234155654907227, "target_z": 3.2187498518960775, "ce": 5.375286102294922, "genuineness": 4.469690799713135, "identity": 0.7771151065826416, "hypothesis": "Bon, quelqu'un a déplacé la petite chaise bleue. Elle était d'ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/87bbface75c795d44ea986270ed4529ecfae8d481cae911f5f521eb86a0b0aa3.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "87dbab3e4b36e34fc4a2ae44cdf6ddbcf33d7a5b93ad726c5a8ed10745c99df9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44cd254848e0a26af6c355ebfe83b30e274fe1a9a0bdead4d26fef97fbc1fa1e", "generation_seconds_batch": 21.26267921400722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.192413806915283, "target_z": 3.5312499552243954, "ce": 5.395142555236816, "genuineness": 4.18099308013916, "identity": 0.5998726487159729, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces. Y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/87dbab3e4b36e34fc4a2ae44cdf6ddbcf33d7a5b93ad726c5a8ed10745c99df9.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "87e58645b79b7b194a62cb60a484706060747690783aaf62047eb10e621abf12", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e17c445d9af7ab1490b08f75f9d8c705347725f803aa0eb07d91c37746325116", "generation_seconds_batch": 15.695513668004423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.79789662361145, "target_z": 6.500000055108436, "ce": 5.665193557739258, "genuineness": 4.482243061065674, "identity": 0.23463942110538483, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/87e58645b79b7b194a62cb60a484706060747690783aaf62047eb10e621abf12.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "87e88086ded1a8473528a0b00dc7b1ef2bc807f9974e660df16e1adafd8473af", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b264a9208c146cfb16248d2c354c3134b241be9651f4e7f1c81ed44715981a4b", "generation_seconds_batch": 22.112113479990512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.020504951477051, "target_z": 5.062500020665664, "ce": 5.689021587371826, "genuineness": 4.7081804275512695, "identity": 0.6418244242668152, "hypothesis": "La porte est encore ouverte. Je posais ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/87e88086ded1a8473528a0b00dc7b1ef2bc807f9974e660df16e1adafd8473af.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "87fe975995be2239129a855781edc4353274d62abfe4590e6d61bb30028d364b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15cedf94de8af2609e8ed425bf8ddfedf22cb5e72f293e83a2097b60522fe26b", "generation_seconds_batch": 22.219423627946526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17763859033584595, "target_z": -0.1943359328717524, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.21598970890045166, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/87fe975995be2239129a855781edc4353274d62abfe4590e6d61bb30028d364b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "88366dfc83cb81cd1ed88fdade30c383e0890b68fa2c654762edf9868bcef821", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4ecf26d15b65986cdb6640ef7d4634da76adf50ac8c0ba01ce3f2475db3b051b", "generation_seconds_batch": 18.97717561502941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9135668277740479, "target_z": 3.0156250051664157, "ce": 5.6532793045043945, "genuineness": 4.469690799713135, "identity": 0.4418490529060364, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/88366dfc83cb81cd1ed88fdade30c383e0890b68fa2c654762edf9868bcef821.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "88c2a675075678bc717119375bc4a48e0920c60b8b7f1dcc94dc5dff1711e280", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af0a3e83d0590240559480ee2cd089e05a4d2b12e623a16d6e51e0884450cd2c", "generation_seconds_batch": 21.471545755979605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26530638337135315, "target_z": -0.03222658693284188, "ce": 6.252951145172119, "genuineness": 4.68307638168335, "identity": 0.6756243705749512, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/88c2a675075678bc717119375bc4a48e0920c60b8b7f1dcc94dc5dff1711e280.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "8905301620a89aa5f09d1530685fdd52eda82409e5541f8153ec6c2053c1c9d2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fe4a89537ce1a8d9ea8b7da471a0da6264acaf659888d0fb1131e3b725be790", "generation_seconds_batch": 22.172967030084692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3078019618988037, "target_z": 5.593750196323804, "ce": 6.006728172302246, "genuineness": 4.457139015197754, "identity": 0.3037396967411041, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8905301620a89aa5f09d1530685fdd52eda82409e5541f8153ec6c2053c1c9d2.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "89b5064218ee4f6591c8ae535c4bc18c09b6629bbbeaf132fec0ecf7d70ad8fb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f4e071207228e9e3cd1d7fdac61a0debb939eccf521a5c4b7c875c0e973762c", "generation_seconds_batch": 22.494362139957957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.091014862060547, "target_z": 3.343749893227405, "ce": 5.824047088623047, "genuineness": 4.7081804275512695, "identity": 0.8206332921981812, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/89b5064218ee4f6591c8ae535c4bc18c09b6629bbbeaf132fec0ecf7d70ad8fb.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "8abb6a98ea5a46bf0df9a8def397effa20399ce86f167a73132b6b6b87924a82", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd345260fcc1f793ba418c95cd3641d4f011d973b21b1c931c50d140285a9240", "generation_seconds_batch": 16.67276754695922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.234663486480713, "target_z": 3.6093752014902205, "ce": 5.3792572021484375, "genuineness": 4.356721878051758, "identity": 0.6472625732421875, "hypothesis": "Ich schlüsse liegen auf dem Küchentisch. Ich suche deine Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.23809523809523808, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8abb6a98ea5a46bf0df9a8def397effa20399ce86f167a73132b6b6b87924a82.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "8ade53614bbe4b0eb1d290d7822ddd2377fe7c5bc77344d0f1d8c3b2f8a89614", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "943c1237f02ab26fedc2fd1dbd28665cb57360d1116100930ddf016ad4583534", "generation_seconds_batch": 14.888574691955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9389164447784424, "target_z": 3.0624998002319184, "ce": 5.935244083404541, "genuineness": 4.557555198669434, "identity": 0.2455539107322693, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8ade53614bbe4b0eb1d290d7822ddd2377fe7c5bc77344d0f1d8c3b2f8a89614.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "8af4502fff53b7dfd5139ddac0b1d64d0c9a7a81903492fd8b3cb76b11e29a19", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dac082797ff0cd36509cc956df5787e6075a3491a87d71779f7d39c2fa0ceb56", "generation_seconds_batch": 20.725076679023914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.158614158630371, "target_z": 3.468749934558732, "ce": 5.250188827514648, "genuineness": 4.400654315948486, "identity": 0.4008764922618866, "hypothesis": "I found the little box it was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8af4502fff53b7dfd5139ddac0b1d64d0c9a7a81903492fd8b3cb76b11e29a19.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "8b075786f435cb43874b4f84cc3122b671a571993477f01cae8efcefb9d9bee1", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c50295e67799170de884d9c31d95d5a094318ba516f1bc92b1d8221431263e1f", "generation_seconds_batch": 16.81504918599967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2093136310577393, "target_z": 3.5624999655572274, "ce": 5.426913261413574, "genuineness": 4.394378662109375, "identity": 0.618776798248291, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8b075786f435cb43874b4f84cc3122b671a571993477f01cae8efcefb9d9bee1.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "8b5ab5073b8646b121a5a168b0e7ea00cde02859ce33f2f29b58998532155885", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "084d2d4e48f8377b7715f6af4b5dcb596e97e97d027bcd845a40257b46bff168", "generation_seconds_batch": 21.617633719928563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4813072085380554, "target_z": 0.36718751119390114, "ce": 6.300607204437256, "genuineness": 4.758388519287109, "identity": 0.7894919514656067, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8b5ab5073b8646b121a5a168b0e7ea00cde02859ce33f2f29b58998532155885.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "8b9ca04fe58bcfac1c74d28bf855e6ebe31faff9d68c4dd44c6c8324a07e4fe4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "506572094fb5124bc5a497c69cda5702744fbae3ab8be058498cfff42edf8cce", "generation_seconds_batch": 15.816768061951734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.981166124343872, "target_z": 3.140625046497743, "ce": 5.879645347595215, "genuineness": 4.796044826507568, "identity": 0.6288354396820068, "hypothesis": "Me he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8b9ca04fe58bcfac1c74d28bf855e6ebe31faff9d68c4dd44c6c8324a07e4fe4.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "8bae742c73ccf120005d7249704c0c9dacd750f4cf73285c9dc19abdc21f0b8b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "881550329fde7137909ef5ff92c24c9e653af96ba474dec4897ea1b4a59bc279", "generation_seconds_batch": 21.554619478061795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.155703544616699, "target_z": 5.312500103328318, "ce": 5.824047088623047, "genuineness": 4.494794845581055, "identity": 0.22451984882354736, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8bae742c73ccf120005d7249704c0c9dacd750f4cf73285c9dc19abdc21f0b8b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "8bc9a5076a6a18ad8cc3e0dd59b37bcce3b87252d2eae90fdccb660cc6344c02", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "659c7743aef07689a36c8d31876f47b1f60813b952939ebe4cab402865ce05be", "generation_seconds_batch": 15.117723227944225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7361187934875488, "target_z": 2.687500117105427, "ce": 5.637393951416016, "genuineness": 4.519899368286133, "identity": 0.6942659616470337, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8bc9a5076a6a18ad8cc3e0dd59b37bcce3b87252d2eae90fdccb660cc6344c02.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "8c2f19d64335f9a26b5855bd03d47b2a7f68a0d14cf38a90514cf6bd11968db5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2beae0514fc913eb9cbc284da3fb90f8c14829f14f07c41d03eaeeb068f7f89f", "generation_seconds_batch": 22.14953198703006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1995494365692139, "target_z": 1.6953123992548897, "ce": 5.95112943649292, "genuineness": 4.570107460021973, "identity": 0.8076452016830444, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8c2f19d64335f9a26b5855bd03d47b2a7f68a0d14cf38a90514cf6bd11968db5.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "8c7778850caadf9da3e9e6663ace0c561d58c48d8c802ada1970b7fa3d65b8aa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bd72a64c9b065b32e737d6c79b0740989f4c0e3e420514f0b4e5682c4c61dddc", "generation_seconds_batch": 14.86443535797298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2460240125656128, "target_z": 1.78125003788705, "ce": 5.784333229064941, "genuineness": 4.482243061065674, "identity": 0.5432456135749817, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8c7778850caadf9da3e9e6663ace0c561d58c48d8c802ada1970b7fa3d65b8aa.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "8cb7e11eb19cb8847118cfb4c92410c1556188f70fa32fed5cc20a40b4c695a3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e1583d9a7c9d50f71206917ebb06a8524c6a7982b8d1db24d6f9424b1e5500f", "generation_seconds_batch": 20.461271884967573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0065157413482666, "target_z": 3.1874998415632456, "ce": 5.9431867599487305, "genuineness": 4.394378662109375, "identity": 0.48904573917388916, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8cb7e11eb19cb8847118cfb4c92410c1556188f70fa32fed5cc20a40b4c695a3.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "8cc4047398730225e8a220fd2618793e510f816d6b56b6d6a62185a3822b69b0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccc7b7c6439710f4f2ea967f40961518c0566b4cacc1bee842539fbb04fd3bff", "generation_seconds_batch": 22.463190381997265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2460240125656128, "target_z": 1.78125003788705, "ce": 5.990842819213867, "genuineness": 4.444586753845215, "identity": 0.7506295442581177, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8cc4047398730225e8a220fd2618793e510f816d6b56b6d6a62185a3822b69b0.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "8ccfe04dfb36a0210d47a16e21edccdd8620977d79bd527427774c59ebe6089f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "915ebda0ad18812928798921fe82c2644e737916bedf48857186555807f105d2", "generation_seconds_batch": 20.91212902998086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5980095863342285, "target_z": 4.281250203212359, "ce": 4.694201946258545, "genuineness": 4.111956596374512, "identity": 0.35534852743148804, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8ccfe04dfb36a0210d47a16e21edccdd8620977d79bd527427774c59ebe6089f.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "8cd09dfa9643cb6a925f6d6e8362a812e436c4e91dcf01230e1419198178a643", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3978b04ee7c41bdfc945fc059c4da4f385fefb482af11b938272c6bec5705088", "generation_seconds_batch": 23.325945831020363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.192425936460495, "target_z": -0.1669921738305246, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.6445794701576233, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8cd09dfa9643cb6a925f6d6e8362a812e436c4e91dcf01230e1419198178a643.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "8cd2fff62be2a9a3ef45d6d9a4d244204156d8f744933f86b8691a357cd10f4a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2007dd035faae126afdd784dc93fffcc5dfc1f1c6ed98d3df8138406ef7d1502", "generation_seconds_batch": 15.033244661986828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.445911169052124, "target_z": 4.000000110216873, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.6052191257476807, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8cd2fff62be2a9a3ef45d6d9a4d244204156d8f744933f86b8691a357cd10f4a.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "8d3fe345ff9e9c6d1ba9a637898226a3a479d65d317b9e57b8ef340b48a44dc2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9d02bd162fa39b3d773fbbbcd9197cddf1b555c99d0d9ea1e42f96211af7430", "generation_seconds_batch": 20.626726294052787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7952680587768555, "target_z": 2.796874932836593, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.6212937831878662, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8d3fe345ff9e9c6d1ba9a637898226a3a479d65d317b9e57b8ef340b48a44dc2.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "8e0943ca9dbf9c6caf0f381a1dac7a9cd78a932fff6a5aff2f5e6b083956b652", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3f1c8447a7f1d3abac20c4b33a6dda7c65e3a593ea24707c0c6bbaa2b3bb51e6", "generation_seconds_batch": 20.91212902998086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.834606885910034, "target_z": 4.718749907004514, "ce": 4.62966775894165, "genuineness": 4.337893962860107, "identity": 0.5625284910202026, "hypothesis": "La puerta sigue apierta, he dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8e0943ca9dbf9c6caf0f381a1dac7a9cd78a932fff6a5aff2f5e6b083956b652.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "8e39baff28db31ade3e0e8c5205374617e30414932e863d0321984385e1334de", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80dcfd58d9f96320e8c6b559820ff48bd0ec7f43fa17bad5c80a6e513c90fbd7", "generation_seconds_batch": 16.15437506500166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.448821783065796, "target_z": 2.156249941447286, "ce": 5.77639102935791, "genuineness": 4.482243061065674, "identity": 0.6569728851318359, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8e39baff28db31ade3e0e8c5205374617e30414932e863d0321984385e1334de.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "8e63c986e8300c31f2965319d8998806a5551c2f0c2bbdd8f036576ad2edb0ad", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d071e26c57e696649dcf7d388c05325be3bfd05df0cb7a5d779c3fa0cd82c4eb", "generation_seconds_batch": 16.4895271420246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5274996757507324, "target_z": 6.000000330650618, "ce": 5.327630043029785, "genuineness": 4.381826400756836, "identity": -0.004405360668897629, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8e63c986e8300c31f2965319d8998806a5551c2f0c2bbdd8f036576ad2edb0ad.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "8e887fe68b8336d93b6d646fb6f43653a01fc7180453c4358c95287363040eb1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acd7bf971830389c64b215c7ed04b8dac4434aaf4676c0c91bf344620886950e", "generation_seconds_batch": 15.605766949942335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7432544231414795, "target_z": 0.8515625611359215, "ce": 6.340320587158203, "genuineness": 4.595211505889893, "identity": 0.2638309597969055, "hypothesis": "The door is pulled to list. The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8e887fe68b8336d93b6d646fb6f43653a01fc7180453c4358c95287363040eb1.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "8ee184492887d1408a185a6e2fb26cef77d092b842623fb3fdadccf2d4d0286a", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f696fcf1b4b363c1284cc87c7046d13445a7dcf1bbf0a7e108b2966fcf7d164", "generation_seconds_batch": 24.348458276013844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3812224864959717, "target_z": 2.031249900115959, "ce": 5.824047088623047, "genuineness": 4.406930446624756, "identity": 0.4149739146232605, "hypothesis": "Someone moved the little blue chair. I used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8ee184492887d1408a185a6e2fb26cef77d092b842623fb3fdadccf2d4d0286a.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "8f0268f2297517ae51f299f13f194217f73d68c23a41109a1359b42e9e31aaad", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0429f4b51c046b3d4e315d1e45cd50690c14fb64dc9bf3fc4dd7d4eea50e0ec8", "generation_seconds_batch": 21.873838106985204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7445685863494873, "target_z": 2.703124901838098, "ce": 5.982900142669678, "genuineness": 4.758388519287109, "identity": 0.5040454864501953, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8f0268f2297517ae51f299f13f194217f73d68c23a41109a1359b42e9e31aaad.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "8f84da043de91c5fc7a96b729958729a0b1443656017854e07021143a59a74d0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62384b611867f6202d4b66febd25dcc54122cd3dac45d1ff6955442432ec5f8b", "generation_seconds_batch": 16.75312477594707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5304102897644043, "target_z": 4.156250161881031, "ce": 6.046441555023193, "genuineness": 4.2751336097717285, "identity": 0.43441444635391235, "hypothesis": "Ik heb het klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8f84da043de91c5fc7a96b729958729a0b1443656017854e07021143a59a74d0.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "8fd065373338e8f901497b99eccbfe47b4846e68d507ec5d7ca705f5ff817096", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7523a2d11893ed3fef2303d6ac86038ca16538bc360cb7571b8610677b60311f", "generation_seconds_batch": 21.62779162894003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8797671794891357, "target_z": 2.9531249845007523, "ce": 5.744620323181152, "genuineness": 4.425758361816406, "identity": 0.35672202706336975, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/8fd065373338e8f901497b99eccbfe47b4846e68d507ec5d7ca705f5ff817096.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "905d5e49cf359ed31a22993d24ba2391c8da7b13595002ba9de2542cb94d6610", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08c905438d6edb0b5db41156537e9c70a90dd0fc16ded421a08bdf54510ea139", "generation_seconds_batch": 14.269536664010957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6318092346191406, "target_z": 4.343750223878023, "ce": 5.629451274871826, "genuineness": 4.143336772918701, "identity": 0.2281205952167511, "hypothesis": "I wrote the number on the envelope. Read it carefully. Check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/905d5e49cf359ed31a22993d24ba2391c8da7b13595002ba9de2542cb94d6610.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "908e027d466c774c70a355d77607c69b01387ec8a20f6c2837d6c3153b6e5815", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12d3dc0c08c65a5990fe89e27066d3e53d3f08e26c719a469104417f261d3970", "generation_seconds_batch": 21.753765398985706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.412111520767212, "target_z": 3.937500089551209, "ce": 5.375286102294922, "genuineness": 4.394378662109375, "identity": 0.4958421587944031, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/908e027d466c774c70a355d77607c69b01387ec8a20f6c2837d6c3153b6e5815.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "909fe967b00cf799a7ea588e3b780ef7f8185ec80a42bbe8a52d66cf212b8414", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8943d1f5c1814ce8b09983929f82c433432582414c115afa153cd4cea33743be", "generation_seconds_batch": 21.288332144962624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.251563310623169, "target_z": 3.640625211823052, "ce": 5.422942161560059, "genuineness": 4.808597087860107, "identity": 0.42741963267326355, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/909fe967b00cf799a7ea588e3b780ef7f8185ec80a42bbe8a52d66cf212b8414.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "90c95d3b2bbbf629123966a47efb26918a171737785a626ffbad9e71b525eea8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71685191c3f1aae5b503f3384b6682bd34da108f5d12762a652667a12f50fa8e", "generation_seconds_batch": 22.021634074044414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3896725177764893, "target_z": 2.04687512571612, "ce": 5.542081832885742, "genuineness": 4.570107460021973, "identity": 0.6711881160736084, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/90c95d3b2bbbf629123966a47efb26918a171737785a626ffbad9e71b525eea8.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "91f35fcaeb78b53e046df7aad932a76d0d2bb70b968007a476b2d21ef4c106fb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd715a318ed37fba640e678798cf6560fcfa0ac15d47d7108f8756107b67bd80", "generation_seconds_batch": 17.807605774025433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.192425936460495, "target_z": -0.1669921738305246, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.46344584226608276, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/91f35fcaeb78b53e046df7aad932a76d0d2bb70b968007a476b2d21ef4c106fb.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "91fa8352f2d0f0a1bb32b7d238047ec9c9d3d162f074247ce0df2d11dfd00b7b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81c6bf970c4a12800b22f05329ab89594226d3c7cddec58e7083d519920edac6", "generation_seconds_batch": 21.486868373933248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 4.679309368133545, "genuineness": 4.293961524963379, "identity": 0.4618834853172302, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/91fa8352f2d0f0a1bb32b7d238047ec9c9d3d162f074247ce0df2d11dfd00b7b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "921cc9d695f224176df6eb254f6b0d062425448cbd0853efa3ed52a1543ae405", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6c706bb59db7366f3be0958962f3562b020f993f760b97fc75127b895f908d60", "generation_seconds_batch": 17.55874256696552, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5246130228042603, "target_z": 0.4472656902260008, "ce": 6.2767791748046875, "genuineness": 4.7834930419921875, "identity": 0.74883633852005, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/921cc9d695f224176df6eb254f6b0d062425448cbd0853efa3ed52a1543ae405.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "92775f6251e67de326ad7d088147f03c268c5638481bc408bd9bd0b330dcbcbe", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dec0c6e19ce0722a357c10e75a1504ff6eb7a066efef13f73c3ba2c6d32866bf", "generation_seconds_batch": 22.214174868073314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2909021377563477, "target_z": 5.562500185990973, "ce": 5.708878040313721, "genuineness": 4.293961524963379, "identity": 0.29549163579940796, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/92775f6251e67de326ad7d088147f03c268c5638481bc408bd9bd0b330dcbcbe.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "92c4c39896da675c75b614a069bc3e73c6a78c0a811041957b1da7aa3ff96c4d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "398f60ba4ee111fcc8e504cb61d192dfa610daaba681147715618a0972dd7117", "generation_seconds_batch": 16.400512019055896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7530186176300049, "target_z": 2.718750127438259, "ce": 5.297844886779785, "genuineness": 4.331617832183838, "identity": 0.4479510486125946, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/92c4c39896da675c75b614a069bc3e73c6a78c0a811041957b1da7aa3ff96c4d.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "93379420a36e0678ab23505f91c25f18d292943280d97f7afe24316c9ef32991", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2609177724e7f7b6c09f65f0cde7631ee52a63cbc7e7637f3fa23f53ccd0e591", "generation_seconds_batch": 26.864096089964733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1699748039245605, "target_z": 1.6406249913893067, "ce": 5.847874641418457, "genuineness": 4.362998008728027, "identity": 0.11635749787092209, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/93379420a36e0678ab23505f91c25f18d292943280d97f7afe24316c9ef32991.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "93e6df730a6fe20003767c983f0520c4cbfac253657c2c7b51dfc52bb732e186", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4560571cf06c55844fd76f0c64a0738dd94b2ed81c535e34b7bab04a90462fb3", "generation_seconds_batch": 22.811970324954018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3698620796203613, "target_z": 3.8593752841528746, "ce": 5.224375247955322, "genuineness": 4.6705241203308105, "identity": 0.7161917090415955, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/93e6df730a6fe20003767c983f0520c4cbfac253657c2c7b51dfc52bb732e186.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "94b3592e9058731e6667a07281e9ac0181a08dc6d74265238f394f353e1ce35d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21ee0ba70c04caca0163a2355eea8555a201f71e99532b3275e871713d3ae1af", "generation_seconds_batch": 20.138355726958252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.412111520767212, "target_z": 3.937500089551209, "ce": 5.049636363983154, "genuineness": 4.118232727050781, "identity": 0.48599550127983093, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/94b3592e9058731e6667a07281e9ac0181a08dc6d74265238f394f353e1ce35d.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "94b9940117e8109c466d350c5ab3a9632d6dbd36673b71546d228fde4ed73885", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee4f04e7ff2304c6a4e58eed415e64b4a6b17ad12fe5955932bf2ccfe4fc5255", "generation_seconds_batch": 25.625156878028065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7614684104919434, "target_z": 2.7343749121709298, "ce": 5.732706069946289, "genuineness": 4.934117794036865, "identity": 0.7015084028244019, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/94b9940117e8109c466d350c5ab3a9632d6dbd36673b71546d228fde4ed73885.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "94bfb2da3074cdaac5108cf796a97784aff3ec4496cd1fef8a0bb1fc5a60c10a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82dc3e0ce4d7271af15033a12efa2aa3b5be3f2a167ec0e5f1ced0b62e28887e", "generation_seconds_batch": 19.636635771021247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8713173866271973, "target_z": 2.9375001997680816, "ce": 6.300607204437256, "genuineness": 4.7834930419921875, "identity": 0.6558674573898315, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/94bfb2da3074cdaac5108cf796a97784aff3ec4496cd1fef8a0bb1fc5a60c10a.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "94f8e82d6ea58a2cb515d4c06743c991dedac313c536c6d1507e6659750af1a5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80d2959c2f100cc8b27af5f14b0c49dd24a79afa8e25c1558d6061155e749f63", "generation_seconds_batch": 21.598469011951238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.054304599761963, "target_z": 5.125000041331327, "ce": 5.462655067443848, "genuineness": 4.607763767242432, "identity": 0.7885342240333557, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/94f8e82d6ea58a2cb515d4c06743c991dedac313c536c6d1507e6659750af1a5.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "95b76c975d6e9f47f591f0c81a3bf7d96aa20742dec5a0f0b8714f1061f9cea4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f44bcde83e55d33fb615d1468dde85ed3d01902100bb4c183e888c43b8b3a73a", "generation_seconds_batch": 19.636635771021247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31336525082588196, "target_z": 0.056640616174039496, "ce": 5.998785495758057, "genuineness": 4.7332844734191895, "identity": 0.6518111228942871, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/95b76c975d6e9f47f591f0c81a3bf7d96aa20742dec5a0f0b8714f1061f9cea4.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "961dbb354f9757f2d62f22586f44166eaddad642bf0e46cc9cdc89888e41232b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e22d559f031e2cf519e05e9fcd2d27d20839153cafc48d6c7c01bbc9d423ca5", "generation_seconds_batch": 16.20963966997806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1670641899108887, "target_z": 3.4843751601588933, "ce": 5.911416053771973, "genuineness": 4.532451152801514, "identity": 0.1827220320701599, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/961dbb354f9757f2d62f22586f44166eaddad642bf0e46cc9cdc89888e41232b.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "96260c8dc3491ade24b820f7585edd93002d3d6aa646a1b387cb173f84a31eb5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "191f776ff673ad7e00d4fb6431786c05bab39a1c3f29c636e2e3fe5dd29ba7c8", "generation_seconds_batch": 21.46140632603783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5781989097595215, "target_z": 6.093749920781622, "ce": 5.95112943649292, "genuineness": 4.444586753845215, "identity": 0.23888829350471497, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in komen.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/96260c8dc3491ade24b820f7585edd93002d3d6aa646a1b387cb173f84a31eb5.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "966ecb81025607b082ea672027bb01ef3897b27d69885daeb1ec75c453309766", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3436087c496df47b66bfcce6623527207136054ed43b11ccac0a805e11e21c24", "generation_seconds_batch": 21.0510713160038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.192413806915283, "target_z": 3.5312499552243954, "ce": 5.569881439208984, "genuineness": 4.582659721374512, "identity": 0.688302218914032, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/966ecb81025607b082ea672027bb01ef3897b27d69885daeb1ec75c453309766.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "971ed681c816c925dca541440cea12f752d14cda255ac58534f2141fb66e0140", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24793f8edd05986e3306625e06f2069ffd188ad79fed611b148ffd7eec2e5738", "generation_seconds_batch": 21.418708279030398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2417991161346436, "target_z": 1.7734376455207146, "ce": 6.078212261199951, "genuineness": 4.444586753845215, "identity": 0.6808081269264221, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/971ed681c816c925dca541440cea12f752d14cda255ac58534f2141fb66e0140.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "979fbd154630a7f4e96a3bc09d6f4694e8e83e2b3b7e87263b23d15ef90e9888", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b561acf890085fe24e1572a8bb651757a93bbeb1429b55f8089ddcc733a3dfd", "generation_seconds_batch": 22.202552821021527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9191060066223145, "target_z": 4.874999958668673, "ce": 5.990842819213867, "genuineness": 4.507347106933594, "identity": 0.5742288827896118, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/979fbd154630a7f4e96a3bc09d6f4694e8e83e2b3b7e87263b23d15ef90e9888.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "97e6f1de2da2cd70c5edc6e2f95555c79cc7b46988292bbe8a19d1bb9f4bab6f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "59790a4be4d0fc3fcf36d76b04b30562922260ad50cf2bb88e4d89a245ac1907", "generation_seconds_batch": 18.30658068100456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.020504951477051, "target_z": 5.062500020665664, "ce": 5.657250881195068, "genuineness": 4.482243061065674, "identity": 0.6004267930984497, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/97e6f1de2da2cd70c5edc6e2f95555c79cc7b46988292bbe8a19d1bb9f4bab6f.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "98313c42059aa46192186de1efd93b2867148f5a9d743530a7bb2a3f54495778", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae53e2659241c8fc04966d0bd08f59b573fd44295ef8e8ce89cc2e398b0e9354", "generation_seconds_batch": 16.705174929113127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302262783050537, "target_z": 3.7343752428215473, "ce": 5.5738525390625, "genuineness": 4.6956281661987305, "identity": 0.8435878157615662, "hypothesis": "Jemand hat einen kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherrekal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/98313c42059aa46192186de1efd93b2867148f5a9d743530a7bb2a3f54495778.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "989a858babee36854087e2ea0f3dd571e970f9c0fbfc27a479d06189075dcd02", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09c19aa0ebcdd07ff41b31a6d94fd6609e00f70525a97e447aaf63df0a2e1f04", "generation_seconds_batch": 21.46140632603783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2571024894714355, "target_z": 5.500000165325309, "ce": 5.80021858215332, "genuineness": 4.419482707977295, "identity": 0.22955939173698425, "hypothesis": "Ik heb het een klein doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/989a858babee36854087e2ea0f3dd571e970f9c0fbfc27a479d06189075dcd02.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "989e8605e9fc749c32bc56084e99e94226a459210e28f84de3ae9dca0cb65da7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58d92f761be2a654dbd826592bb1086cea9126a1f67b88520f92125772281133", "generation_seconds_batch": 20.082475688075647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0036051273345947, "target_z": 5.0312500103328315, "ce": 5.808161735534668, "genuineness": 4.306513786315918, "identity": 0.31676894426345825, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/989e8605e9fc749c32bc56084e99e94226a459210e28f84de3ae9dca0cb65da7.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "98b637f61fb71c1c99d8c6616faf170145c4700e37b0d0656eaba806935a415e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66d7634a4d00af3721232b3a2a1d40220afebd390f527b3f2c0027348214a888", "generation_seconds_batch": 15.872356152976863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750108003616333, "target_z": 4.562500296207845, "ce": 5.752562999725342, "genuineness": 4.758388519287109, "identity": 0.68416827917099, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/98b637f61fb71c1c99d8c6616faf170145c4700e37b0d0656eaba806935a415e.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "9993a9b324f27bc1a0ff56f0823ce726a85e6db122b4cf51325f1c61ff229f3e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ed36589f6cd0be7d4a44fc7f263a6c8ce68032c5eb294815c68926ab7b32051f", "generation_seconds_batch": 24.715185934095643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.803718090057373, "target_z": 2.8125001584367544, "ce": 5.824047088623047, "genuineness": 4.337893962860107, "identity": 0.4964119791984558, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9993a9b324f27bc1a0ff56f0823ce726a85e6db122b4cf51325f1c61ff229f3e.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "999caed0fc09898bbac81010961529cf06b82d0051f1c54c07cfc4f9c392b0fc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba1cd6dc666ff31f531cc48c44d5c5634cf776678a4bd03554bc51bec73c2010", "generation_seconds_batch": 20.386862203013152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6149094104766846, "target_z": 4.31250021354519, "ce": 5.3514580726623535, "genuineness": 4.632867813110352, "identity": 0.7358222007751465, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/999caed0fc09898bbac81010961529cf06b82d0051f1c54c07cfc4f9c392b0fc.mp3" }, { "id": "heldout-de-0", "language": "de", "sentences": [ "Deine Nachricht kam, als ich schon weg war.", "Ich las sie zweimal... dann legte ich das Handy weg.", "Sag mir, wann wir reden können." ], "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-0", "key": "99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c37797f5d9f43e3c6addf61f8d482acce9398bdf8e5c5c146d9e186826b96f7", "generation_seconds_batch": 17.625090943067335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28590303659439087, "target_z": 0.005859349383187805, "ce": 6.2767791748046875, "genuineness": 4.7458367347717285, "identity": 0.7552452683448792, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "99d0a4f060edb092dab8c6bde82da6eca9fa856bb6fcb1e7f5521b1c4fbfac61", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eaafb3c792c753b094a8fd8018c02a086cbb34ac4cef3de18040bfbc3535c9bc", "generation_seconds_batch": 15.058596579008736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8797671794891357, "target_z": 2.9531249845007523, "ce": 5.788304805755615, "genuineness": 4.369274139404297, "identity": 0.3092864751815796, "hypothesis": "The keys are on the kitchen table. I checked the drawer and looked outside the window. Take them with you when you leave.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/99d0a4f060edb092dab8c6bde82da6eca9fa856bb6fcb1e7f5521b1c4fbfac61.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "9a06a6841998e15b6ce7ed452c70c7dbe0a75f15a0e0414b8199bc6a1539b0be", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "306d88834ed9ceb6629600a182977ddf01a284e5b07822a9bcafde7f4f9366bf", "generation_seconds_batch": 21.664111986989155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2087976336479187, "target_z": -0.13671874009770285, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.3880094587802887, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9a06a6841998e15b6ce7ed452c70c7dbe0a75f15a0e0414b8199bc6a1539b0be.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "9aa5dd2d98832f52ca33cbe43df92147caa97fd68eb59434af8ebda67cd8752b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f618fbd90902402cd891624a55e42ecc9670b2db3fe4b4c7a57a66f66913b927", "generation_seconds_batch": 21.788898220984265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9022061824798584, "target_z": 4.843749948335841, "ce": 5.331601142883301, "genuineness": 4.406930446624756, "identity": 0.678238034248352, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9aa5dd2d98832f52ca33cbe43df92147caa97fd68eb59434af8ebda67cd8752b.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "9ac0e71238d3fbf35c5f336a9054326f0d3002f162cdaced308ab6f454488ecb", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6263c4be37b4ba6bce18839111c29cecc7673b2a2b04ceb42131c0faf3427e35", "generation_seconds_batch": 24.454453208949417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8544175624847412, "target_z": 2.9062501894352497, "ce": 5.879645347595215, "genuineness": 4.68307638168335, "identity": 0.775858998298645, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit bist.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9ac0e71238d3fbf35c5f336a9054326f0d3002f162cdaced308ab6f454488ecb.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "9ac7db8550ed734cc4974762cf1abdec5c08f67eaffbf5c9c4a195a117e2b78b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac628790cc47b61c1b7a0b964f4758969b1637de6307fa125e732682ad4b6b13", "generation_seconds_batch": 22.93379846296739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46281099319458, "target_z": 4.031250120549704, "ce": 6.078212261199951, "genuineness": 4.482243061065674, "identity": 0.4314787983894348, "hypothesis": "De deur staat nog open. Ik heb je het jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9ac7db8550ed734cc4974762cf1abdec5c08f67eaffbf5c9c4a195a117e2b78b.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "9afb9bd101b13d2abdc0c388254bdf22b55bd8982fa5aef1bb966456edbabc63", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38c559bbfa2e390fb22e725c3050eebc7ad3cee03f4a97eb9644777b3e6db597", "generation_seconds_batch": 15.377039915067144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5417709350585938, "target_z": 2.3281252187116066, "ce": 5.974957466125488, "genuineness": 4.607763767242432, "identity": 0.22701220214366913, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9afb9bd101b13d2abdc0c388254bdf22b55bd8982fa5aef1bb966456edbabc63.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "9b3a37dcdbc11c3789fd89054a02ef0d09186618defdfbb5afa209951c19e2b2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "426e555dbdc574711c8289d8d24d23f11d3eefa475a88fa49bcdcff99a4eaf22", "generation_seconds_batch": 21.62779162894003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2037744522094727, "target_z": 1.7031250120549704, "ce": 5.689021587371826, "genuineness": 4.18726921081543, "identity": 0.622645378112793, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9b3a37dcdbc11c3789fd89054a02ef0d09186618defdfbb5afa209951c19e2b2.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "9b66d5a04977f2c44c05e8c5e369894548e11870ad15815b20e747b604d33a9c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bca0c8706b2357a6c6a0fb26812bc2917f8fba49085240315fc5578b9f3969f", "generation_seconds_batch": 13.98071896203328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1670762002468109, "target_z": -0.2138671893297723, "ce": 6.1894097328186035, "genuineness": 4.381826400756836, "identity": 0.555029034614563, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9b66d5a04977f2c44c05e8c5e369894548e11870ad15815b20e747b604d33a9c.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "9be2d758c099396d7a25f4fc39d7eea3d24f7b2f43afdb77ec27668a71ca749a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "94633fb232f015c33c13132b83a19fe048a04c6808de4a51860ee3a5bce9e9ff", "generation_seconds_batch": 22.71827597497031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2402026653289795, "target_z": 5.4687501549924775, "ce": 5.053607940673828, "genuineness": 4.457139015197754, "identity": 0.5830325484275818, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9be2d758c099396d7a25f4fc39d7eea3d24f7b2f43afdb77ec27668a71ca749a.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f540a0f61ce0ca4fcf513c7cc2456f07e1a889f24aa187e2790237e00611e075", "generation_seconds_batch": 14.036032180069014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.574256181716919, "target_z": 0.5390624578076034, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.6398144364356995, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "9c7a4f6fd16e5ab8ed30a55d2fd583a4e8dba3beca261bdddd575047b4f3a631", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c03f1ce6d124e14e62e7199ae31965c17334fd673cf701b3d6d05abc2282e6ee", "generation_seconds_batch": 20.503217136953026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.017876386642456, "target_z": 1.3593748983938205, "ce": 6.221180438995361, "genuineness": 4.68307638168335, "identity": 0.2955487370491028, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9c7a4f6fd16e5ab8ed30a55d2fd583a4e8dba3beca261bdddd575047b4f3a631.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6754c5837194ee71571885b88d9d31f32d10f301fba0b432c2289b947e4ddbd", "generation_seconds_batch": 13.602856416953728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23678794503211975, "target_z": -0.08496095181527741, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.5870826244354248, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "9daf8eaa64d6397d2f18219938a8cbedc2832dcf91744f402bc8a1a6b57224a1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86de287eeabce2dbeb0601300fa5ee4b190b2f7ced66ae4a615b4a84be0c7138", "generation_seconds_batch": 22.818801123998128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.443000555038452, "target_z": 5.843750278986459, "ce": 5.514282703399658, "genuineness": 4.168440818786621, "identity": 0.17872004210948944, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9daf8eaa64d6397d2f18219938a8cbedc2832dcf91744f402bc8a1a6b57224a1.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "9e35b090053211460b09c99763e27f55ae42c191b32332f9cda2a25164395a7b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5eaf939f04eda967c4d397c2e615d856292d3e33c9ad188eb6e736f1df1f0d7", "generation_seconds_batch": 22.90531655610539, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.981166124343872, "target_z": 3.140625046497743, "ce": 6.038498878479004, "genuineness": 4.557555198669434, "identity": 0.7798819541931152, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9e35b090053211460b09c99763e27f55ae42c191b32332f9cda2a25164395a7b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "9e39e0a3e7663d56142ad9556f784b628fd04645f519e1c084173090f6f77a95", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "010e34ef4e4cdfb2c1c73daf5655b825c88b71bd65238fd8030bc7230facb625", "generation_seconds_batch": 17.26740084704943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.769918441772461, "target_z": 2.750000137771091, "ce": 5.601652145385742, "genuineness": 4.557555198669434, "identity": 0.7062796354293823, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9e39e0a3e7663d56142ad9556f784b628fd04645f519e1c084173090f6f77a95.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "9f6a5dbffdae9f272f2303c1c6decd4f07d824276e552d0fef8831aa2bd351d1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d4e911d922d9cacdc9c118957ed81738b4283824b92b9babfb1bb64389ad702", "generation_seconds_batch": 21.861585121019743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18397602438926697, "target_z": -0.1826171789969405, "ce": 6.316492557525635, "genuineness": 4.7332844734191895, "identity": 0.5204079151153564, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9f6a5dbffdae9f272f2303c1c6decd4f07d824276e552d0fef8831aa2bd351d1.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "9fd023c0498c1ebabf0a41847500398ccc4ddf96f36e1ecffe73b76db03653c6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5732893c0a58ba3cf24b585060a2f60402331512132aaae7360493f03e999d03", "generation_seconds_batch": 16.20963966997806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.496610641479492, "target_z": 4.093750141215368, "ce": 5.780362129211426, "genuineness": 4.256305694580078, "identity": 0.33939328789711, "hypothesis": "De de deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/9fd023c0498c1ebabf0a41847500398ccc4ddf96f36e1ecffe73b76db03653c6.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "a014047574da6df3e8d34f9044dc1b1aa38b1e400371b713fc501c4ac0bc7442", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd59cebd998b86c914926b044b9fc0504c3e2e091f56b34ea5586ee6e3349ca6", "generation_seconds_batch": 21.592552946996875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1784247159957886, "target_z": 1.6562499965557227, "ce": 6.022613525390625, "genuineness": 4.419482707977295, "identity": 0.38578617572784424, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a014047574da6df3e8d34f9044dc1b1aa38b1e400371b713fc501c4ac0bc7442.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "a02643908e4db39cde70fcc310682e9372b59dfddb0ed0072c5c7fcb995db4a1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2edad06bbf32c10251ac968936d9431513182ef7428ff7904af62b60d12182b1", "generation_seconds_batch": 23.063552314066328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750108003616333, "target_z": 4.562500296207845, "ce": 5.95112943649292, "genuineness": 4.293961524963379, "identity": 0.32488322257995605, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a02643908e4db39cde70fcc310682e9372b59dfddb0ed0072c5c7fcb995db4a1.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "a0854395a2e2169256831a1fec88a489143f798db926f9ee4d83774adb7e00d5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce86311941654b23ba8a3e5ae0a91e36f01e86b1bd83c7db4d7bad8fff341861", "generation_seconds_batch": 20.749189878930338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8713173866271973, "target_z": 2.9375001997680816, "ce": 5.879645347595215, "genuineness": 4.7834930419921875, "identity": 0.6562191247940063, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a0854395a2e2169256831a1fec88a489143f798db926f9ee4d83774adb7e00d5.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "a0c128de939157e593ac2c52382adc20b0742849f9810b18009db6d8fb504111", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfdf831fce2e20d8f38d09ec2306cff706a1e7bfb435218a52b88917d1eea48d", "generation_seconds_batch": 25.238044171012007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.175513982772827, "target_z": 3.4999999448915635, "ce": 5.289902210235596, "genuineness": 4.293961524963379, "identity": 0.33061933517456055, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a0c128de939157e593ac2c52382adc20b0742849f9810b18009db6d8fb504111.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "a0e2116e67ffdec90477c7eaf998b6960198f4384f7670a0bfd451d8a30fcfda", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f34f546936a38f1be9f7940e5b8bf0a289cb89a6ff4f6fa81c7850c0c5a93b11", "generation_seconds_batch": 19.926106580067426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0305513143539429, "target_z": 1.382812516360317, "ce": 5.764476776123047, "genuineness": 4.369274139404297, "identity": 0.47205841541290283, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a0e2116e67ffdec90477c7eaf998b6960198f4384f7670a0bfd451d8a30fcfda.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "a1360b3d650eca0d9e2fed460b0fc3b304aa01c15dba5fe6537367f5ebd4655c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fc575dc2be0ca498851063b9c1b4789bbd18b3ec7dd97a04f0b3f420de5b972", "generation_seconds_batch": 16.575806188047864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.020504951477051, "target_z": 5.062500020665664, "ce": 5.375286102294922, "genuineness": 4.6705241203308105, "identity": 0.7322670221328735, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a1360b3d650eca0d9e2fed460b0fc3b304aa01c15dba5fe6537367f5ebd4655c.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "a146c5cd70eb97d89b4e4a0fbeeaa08012afce145343df1cb2c579730bba35c5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe19ed8b95c49240619fe2e13c471564942524342fd9ac0a471ee69f143e4d82", "generation_seconds_batch": 16.252663746941835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3896725177764893, "target_z": 2.04687512571612, "ce": 5.990842819213867, "genuineness": 4.758388519287109, "identity": 0.6958670616149902, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a146c5cd70eb97d89b4e4a0fbeeaa08012afce145343df1cb2c579730bba35c5.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "a186d3d00ac2e5b67e504a8f47abe493ee0f7a807919672517514e086343894d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a06cdc78f5802b02a7ea1546a78345dde062a455a5407e1aac8d5505dc83c3f8", "generation_seconds_batch": 25.474087564041838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8544175624847412, "target_z": 2.9062501894352497, "ce": 5.974957466125488, "genuineness": 4.846253395080566, "identity": 0.6799155473709106, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a186d3d00ac2e5b67e504a8f47abe493ee0f7a807919672517514e086343894d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "a1a1d849eb1fad4219c3ae83aac470c2629367f5fddd6ec164c89a1a3b432fee", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bd7cce9f7f13f4b323de44660ec597c0b8c6f137811a5785e55c428224fac08", "generation_seconds_batch": 21.801862300024368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.158614158630371, "target_z": 3.468749934558732, "ce": 5.903473377227783, "genuineness": 4.7332844734191895, "identity": 0.615806519985199, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a1a1d849eb1fad4219c3ae83aac470c2629367f5fddd6ec164c89a1a3b432fee.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "a21aba524e45c3839d11c22e601e4fc5ca3c9b7396b0af5990a8ee6bc73399d5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab6b6e9cd30aa63c4a5be66cb7a721e7ae10ce8b25c2ee6e769efff2b0be71d0", "generation_seconds_batch": 15.328862956026569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.967014789581299, "genuineness": 4.375550270080566, "identity": 0.23312826454639435, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a21aba524e45c3839d11c22e601e4fc5ca3c9b7396b0af5990a8ee6bc73399d5.mp3" }, { "id": "heldout-de-4", "language": "de", "sentences": [ "Ich schrieb die Nummer auf den Umschlag.", "Lies sie genau... und prüfe die letzten beiden Ziffern.", "Ruf an, wenn du Zeit hast." ], "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-4", "key": "a2a193117ac1a0694755948457681ddaf022f8445b48f4a0fbfbab91716619bf", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed30998a7a3fe0ae2060886624d6d8c973511aec0696fd2a2580925692e45879", "generation_seconds_batch": 15.604210445890203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.074115037918091, "target_z": 3.312499882894573, "ce": 5.442798614501953, "genuineness": 4.557555198669434, "identity": 0.558521032333374, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, sieh sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a2a193117ac1a0694755948457681ddaf022f8445b48f4a0fbfbab91716619bf.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "a35816ae6d9596c9fa69fa2c62a530f969c3f3b9c0c1d894f96fd8b4baea9bf0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ad4aa59496068702bfd9f34afe15ddac454ba1c6c56f9bdc2d5e703ec205647", "generation_seconds_batch": 20.519363917061128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2753406763076782, "target_z": -0.013671851966395757, "ce": 6.006728172302246, "genuineness": 4.570107460021973, "identity": 0.7338653802871704, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a35816ae6d9596c9fa69fa2c62a530f969c3f3b9c0c1d894f96fd8b4baea9bf0.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "a364908a065a95a446450158ac2f92fc7124e7706ff7d7ad0cc8d051616d9d01", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0270085da09e8770e54457e51e4f636e95596cf4c23d40ba81ea1b5b980b9100", "generation_seconds_batch": 21.926476173917763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4150221347808838, "target_z": 2.093749920781623, "ce": 5.7247633934021, "genuineness": 4.6956281661987305, "identity": 0.7220577001571655, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a364908a065a95a446450158ac2f92fc7124e7706ff7d7ad0cc8d051616d9d01.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "a3d60e079d7305f924dd83083198ed3a1b4034b52003798df5996af7bdf75efa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfc89d94f97c8fe39be11728626969fa8dbb70c8fcbf6c968385fc6115a46686", "generation_seconds_batch": 23.13824164296966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.834606885910034, "target_z": 4.718749907004514, "ce": 5.855817794799805, "genuineness": 4.482243061065674, "identity": 0.6289817094802856, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a3d60e079d7305f924dd83083198ed3a1b4034b52003798df5996af7bdf75efa.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "a4a1eead7918d26aa7037bd51d16454091e8ef2578a24488c65f18305f304876", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f902b7cf653200686708bfa7139944eaf639e54895d7a280344d92f22b6cb74e", "generation_seconds_batch": 20.815682041924447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1895031929016113, "target_z": 5.375000123993981, "ce": 5.184661865234375, "genuineness": 4.093128204345703, "identity": 0.287612646818161, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je kleur bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a4a1eead7918d26aa7037bd51d16454091e8ef2578a24488c65f18305f304876.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "a52e6033c4e6f7c0c414ff3b667457918b7e53e6e0cab443eacf4ff9f41ffda7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8288262af85517879722be9e4b4ed289e3b1a222538541aa161e9303b560adb6", "generation_seconds_batch": 22.311523201991804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6938691139221191, "target_z": 2.6093748708396025, "ce": 5.919358730316162, "genuineness": 4.7458367347717285, "identity": 0.6488790512084961, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a52e6033c4e6f7c0c414ff3b667457918b7e53e6e0cab443eacf4ff9f41ffda7.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "a6425f5cf41c54f7f976b2d2851bb97310292920b15223703c71ac38d842acb2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3b58ee2e800d0de78ef3b700c91f0495a890421cabed92a2e542d4d7bd2f4808", "generation_seconds_batch": 22.58910707605537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 5.792276382446289, "genuineness": 4.595211505889893, "identity": 0.6404394507408142, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a6425f5cf41c54f7f976b2d2851bb97310292920b15223703c71ac38d842acb2.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "a6aea5cca272fea2ffbe1ca329c9d6b5b93f7f8dce40894d75deee7fab5868b1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec7dfb84952884f38813c874e6cdca31092f6323cd655a50fc9641e5553380b6", "generation_seconds_batch": 20.885591575992294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5105998516082764, "target_z": 5.9687503203177865, "ce": 5.522225379943848, "genuineness": 4.243753433227539, "identity": 0.4765183925628662, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a6aea5cca272fea2ffbe1ca329c9d6b5b93f7f8dce40894d75deee7fab5868b1.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "a6c13408c3d3e109eb753d0b5473a281a431c8ca6ed5c7214cdcc84708f62dc0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1a37f7f885b652ec8fb078270cc0a3e58afa4745c3f487d862c723f87d0393e", "generation_seconds_batch": 20.414894553949125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.233349084854126, "target_z": 1.7578124199205534, "ce": 5.609594821929932, "genuineness": 4.507347106933594, "identity": 0.6231739521026611, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a6c13408c3d3e109eb753d0b5473a281a431c8ca6ed5c7214cdcc84708f62dc0.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "a6e0f3634d9206eb90b442c721bd7cef20fd5e0c9222139e016ffb41758d4ece", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9f5da52ec006ee6062f2a159a1f8fd0ee359db91b8b8bd7aceaea0c7eca2b35", "generation_seconds_batch": 21.4460113090463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32894477248191833, "target_z": 0.08544921256106427, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.33694759011268616, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a6e0f3634d9206eb90b442c721bd7cef20fd5e0c9222139e016ffb41758d4ece.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "a7f935a4c3464888eb19d2f32376b498668c930b1f954878b2bc77c7c08dd924", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e0751ecaa9887fc072a58f9cbbac24f63bd538d5d7c177af9daec93eb510eb3", "generation_seconds_batch": 15.880102566094138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2431132793426514, "target_z": 3.6249999862228908, "ce": 5.585766792297363, "genuineness": 4.821148872375488, "identity": 0.6710466742515564, "hypothesis": "Me he encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a7f935a4c3464888eb19d2f32376b498668c930b1f954878b2bc77c7c08dd924.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "a88acc933f92750ae2ef838a74d8bab3d7686f372b55d2ddea4fd5d8c0d34944", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd7eba84dabb9ba6f602e4b458bc8bea4bc86737ce19a6dbd391f03dd29055b2", "generation_seconds_batch": 20.277096166973934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.037404775619507, "target_z": 5.093750030998495, "ce": 5.375286102294922, "genuineness": 4.482243061065674, "identity": 0.6687562465667725, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a88acc933f92750ae2ef838a74d8bab3d7686f372b55d2ddea4fd5d8c0d34944.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51c36d514ae961f6d388bf490e2e8100b61c551ac08c2da20e2111b9606aa1de", "generation_seconds_batch": 15.969395963009447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4211015999317169, "target_z": 0.25585937693740596, "ce": 6.109982967376709, "genuineness": 4.344170093536377, "identity": 0.6374694108963013, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "a8f3b619eeb103364df9d8a979177dd64f53eabf2a2c0375082cc679516192b2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cc81a888f970fbc828200e7a9097b312849fb6df7e8c317d5a4f412e532f319", "generation_seconds_batch": 21.94367308798246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25738459825515747, "target_z": -0.04687501549924771, "ce": 6.109982967376709, "genuineness": 4.6705241203308105, "identity": 0.3303910195827484, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a8f3b619eeb103364df9d8a979177dd64f53eabf2a2c0375082cc679516192b2.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68bac190c2831989956544a2df762e7fa23bbdecbbb44539ac9d76f7dc00a5f8", "generation_seconds_batch": 16.27601595898159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31019654870033264, "target_z": 0.05078126679085169, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.7960637807846069, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "a95a5faf8d15e67fee2db9759262ad4e0a329309fe67853fd654b4d4459ad53b", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "715d20bf41dad697c94a7e5816f1dbde2ad688a9be86ee3366ef35e066988e7f", "generation_seconds_batch": 16.184033751953393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2832624614238739, "target_z": 0.0009765766000100738, "ce": 6.157639026641846, "genuineness": 4.243753433227539, "identity": 0.646801233291626, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a95a5faf8d15e67fee2db9759262ad4e0a329309fe67853fd654b4d4459ad53b.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "a9cc8031c410f15c2e868c3f8d935fac65c1ae8581794def890f5f94d2f2ce41", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "40888cf5f632378ec32333e4de358c1d04dcd624925e5334c55d29dae5b599c4", "generation_seconds_batch": 22.943622312974185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2375741004943848, "target_z": 1.765625032720634, "ce": 5.855817794799805, "genuineness": 4.381826400756836, "identity": 0.33865079283714294, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/a9cc8031c410f15c2e868c3f8d935fac65c1ae8581794def890f5f94d2f2ce41.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "aa51ade2dbf8efa110be36d86c2e42ec24c309d5ba93e3043841f93920a86b85", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24a6aa79447e6af45d9f42310c893fb95ca6f8450564984808af5ba53ee5bfa5", "generation_seconds_batch": 20.926585896057077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9698054790496826, "target_z": 4.9687499896671685, "ce": 4.993044853210449, "genuineness": 4.532451152801514, "identity": 0.66605544090271, "hypothesis": "Der Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aa51ade2dbf8efa110be36d86c2e42ec24c309d5ba93e3043841f93920a86b85.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "aa9cd07ebed5f5c600208e403b5e89c3583d998fa41b212a15dbbab005706fa3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab2c489c8f8f736a014a316125810a727176b6d147120110b5d66ad4e496d9fc", "generation_seconds_batch": 25.313960302970372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5079712867736816, "target_z": 2.265625198045943, "ce": 5.506340026855469, "genuineness": 4.444586753845215, "identity": 0.5416826605796814, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aa9cd07ebed5f5c600208e403b5e89c3583d998fa41b212a15dbbab005706fa3.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "aaa9aec4396f87efe2d7bd34f0cf9a22f8dadc3e9afaae5caaca263c66a10dff", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d9567964efb1875c4406f028c8ac5e80c6a5e622f15bc484ee2e7488de3842d", "generation_seconds_batch": 22.38210699299816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0305513143539429, "target_z": 1.382812516360317, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.5038169622421265, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aaa9aec4396f87efe2d7bd34f0cf9a22f8dadc3e9afaae5caaca263c66a10dff.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "aabf6149ea7865de1ee06505fc246fd9ed3409c654983041e89275f503a496ab", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e17204def742d7e424023476e5b438557df241d9207abbaf1280dee5205c2165", "generation_seconds_batch": 16.046483009005897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2655704617500305, "target_z": -0.031738271078618686, "ce": 6.0305562019348145, "genuineness": 4.6203155517578125, "identity": 0.7673503160476685, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aabf6149ea7865de1ee06505fc246fd9ed3409c654983041e89275f503a496ab.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "aac942486b985aa598e726bcc697100ef6276f2525fd51ecc5c6400aeff7c104", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0c40998b1bf19d9e5921a292c9f9ccd6220f0179bfe7cac444fd2fedc5e02d1b", "generation_seconds_batch": 22.494362139957957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2460240125656128, "target_z": 1.78125003788705, "ce": 5.804190158843994, "genuineness": 4.6203155517578125, "identity": 0.7686827182769775, "hypothesis": "J'ai trouvé le la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aac942486b985aa598e726bcc697100ef6276f2525fd51ecc5c6400aeff7c104.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "aad261966c498eabf75152d9aa1e40e64919573a0659ba25a58b8d9688754f26", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "480364bfe7da26c24282f839a888a05dfe2cdce3d5df0304040f60ea43ecb11f", "generation_seconds_batch": 22.50948345893994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.767007827758789, "target_z": 4.593750306540677, "ce": 5.7128496170043945, "genuineness": 4.770940780639648, "identity": 0.686071515083313, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aad261966c498eabf75152d9aa1e40e64919573a0659ba25a58b8d9688754f26.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "ab5b4183527444454a2cc2e2e878c6c5d64bfe43437d844b8954b14c3ff33608", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c3b6e40e3eb1e4933d3a6b9c0dbd100c544635f4ea7e7b7f1c82a9fb94028fe", "generation_seconds_batch": 21.232956737978384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.817707061767578, "target_z": 4.687499896671682, "ce": 5.7128496170043945, "genuineness": 4.6203155517578125, "identity": 0.11974509060382843, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ab5b4183527444454a2cc2e2e878c6c5d64bfe43437d844b8954b14c3ff33608.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ff86953c380feb0c94c2f4cd77702ffcbcf63d12ae142a2b399d207764fc9f4", "generation_seconds_batch": 15.201117038959637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3170620799064636, "target_z": 0.06347654215723737, "ce": 6.4515180587768555, "genuineness": 4.381826400756836, "identity": 0.12544526159763336, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "ab90b1cef65017788386e5e9f7b7f6811f2984ba3366adac384170c9b6f66f2c", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65acb5dec3c62bd49f5a405bca81ace920e29ad5c7282749ab818b22d92c7646", "generation_seconds_batch": 15.673256810056046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3347480297088623, "target_z": 1.9453124819175442, "ce": 6.24500846862793, "genuineness": 4.557555198669434, "identity": 0.2697983980178833, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ab90b1cef65017788386e5e9f7b7f6811f2984ba3366adac384170c9b6f66f2c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "ac26723b756d9f919f0bab4e372f58cfde138be2164745d258b9b21d52349bb0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "69934b7f5711928bd87f24b1b9d459a9d1fd9c8bc6adeb00032e03e2ff02a308", "generation_seconds_batch": 15.77122448303271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.699408531188965, "target_z": 4.46875026520935, "ce": 5.327630043029785, "genuineness": 4.545003414154053, "identity": 0.8354905843734741, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten gemeinsam hineinschauen.", "wer": 0.1875, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ac26723b756d9f919f0bab4e372f58cfde138be2164745d258b9b21d52349bb0.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "acb96650947d0d6d1cbde83b8227941879c221fdd029bbd149d9887f8f9f679f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42540f81fa27de3bae01776815a6a8f977abb7047687f8e53855676b30d7e638", "generation_seconds_batch": 20.749189878930338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8459675312042236, "target_z": 2.8906249638350885, "ce": 6.062326908111572, "genuineness": 4.934117794036865, "identity": 0.7032821178436279, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/acb96650947d0d6d1cbde83b8227941879c221fdd029bbd149d9887f8f9f679f.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "ad05a4f97f9bd443040bded7029fcd46dc848fd27d6911e7e5e21b9860b66853", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0839963807cffb84ce88065c566339ad5b8320377b519292825cefecbbe8ee39", "generation_seconds_batch": 16.184033751953393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6178200244903564, "target_z": 2.4687500447756046, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.7287842631340027, "hypothesis": "Ja, ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ad05a4f97f9bd443040bded7029fcd46dc848fd27d6911e7e5e21b9860b66853.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "ad6e1903f4cdfa6ff21361e4c10ead18981320731d1d1f9f058448f5f94a35d3", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99b42c4f45a4d3a575352e0bb98e76d6586746f0a81f5169c67120912baec4b5", "generation_seconds_batch": 15.776844699052162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8628673553466797, "target_z": 2.9218749741679204, "ce": 5.748591423034668, "genuineness": 4.507347106933594, "identity": 0.6266951560974121, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ad6e1903f4cdfa6ff21361e4c10ead18981320731d1d1f9f058448f5f94a35d3.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "ad85baba46eec6fe83eb961e37618bf4a45c105e70e9320ba2856b086fd17506", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d634b1b00af7234738d19071d2618279213742c177d15a1ef57308ad9e382fb", "generation_seconds_batch": 22.86662848200649, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.445911169052124, "target_z": 4.000000110216873, "ce": 5.601652145385742, "genuineness": 4.65797233581543, "identity": 0.7419528365135193, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ad85baba46eec6fe83eb961e37618bf4a45c105e70e9320ba2856b086fd17506.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "ad871f2cfa9da3dfe4b83b9552a6cdeb881a8068d883432c29c5796c95438ee0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03c8b0045cae72cd1b6084c739f6d5db97e711971a68c5ca7c2304c8ec47d7fd", "generation_seconds_batch": 23.13824164296966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.088104248046875, "target_z": 5.187500061996991, "ce": 5.95112943649292, "genuineness": 4.582659721374512, "identity": 0.49224263429641724, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ad871f2cfa9da3dfe4b83b9552a6cdeb881a8068d883432c29c5796c95438ee0.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "ad8f7d490de1daf89712cfcce5e28b5ffe110bc7536d802641f283b626475e9c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a93f966aa1dba9e7efe572346d05436542ba3f7a5278fb11fb7b80d40bf74f5b", "generation_seconds_batch": 15.033244661986828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 5.871703147888184, "genuineness": 4.532451152801514, "identity": 0.4855393171310425, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ad8f7d490de1daf89712cfcce5e28b5ffe110bc7536d802641f283b626475e9c.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff243c4f6d2cb5c9682d9e6adcc607bab14e41e45c8d539bf891bc81261946f0", "generation_seconds_batch": 16.236490941955708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4475075602531433, "target_z": 0.3046874905282375, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.6407958269119263, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "adea40ee9b5e78082bbf5879ad977ac3a7a3842331052d89c64e7df677ca0be5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "baab815afc062b8f653cafe2d438d364ea75f6f205c66707816d5bcb965ffba3", "generation_seconds_batch": 20.81701773207169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1895031929016113, "target_z": 5.375000123993981, "ce": 5.7247633934021, "genuineness": 4.883909225463867, "identity": 0.7108764052391052, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/adea40ee9b5e78082bbf5879ad977ac3a7a3842331052d89c64e7df677ca0be5.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd5ce13fd77bc0e9e0202d9284955f85cfbb8c125ee0f49d133538066eb6d0f7", "generation_seconds_batch": 14.93534094991628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13169220089912415, "target_z": -0.27929688468702984, "ce": 6.459460258483887, "genuineness": 4.13078498840332, "identity": 0.3717558681964874, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "ae4eebca3fa9f4c52a242cc785f48456b377d47e6d0fdc1a128a3979d7835ac1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25065cacceb159cd773797449ed445cb9915353a72d32cff18e4e99a93cf5aa0", "generation_seconds_batch": 21.101911879959516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6516196727752686, "target_z": 2.531250065441268, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.48545560240745544, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ae4eebca3fa9f4c52a242cc785f48456b377d47e6d0fdc1a128a3979d7835ac1.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "ae514fbbce4dfd5464b738e6df04cca37a559a74732cf3a861be62328d552ad5", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "886fd83e58ed320deea6f714be60041721e1397e2ee8471872a9a855464d857e", "generation_seconds_batch": 15.9742321530357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9668948650360107, "target_z": 6.812500158436754, "ce": 5.700935363769531, "genuineness": 4.356721878051758, "identity": 0.3792901635169983, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ae514fbbce4dfd5464b738e6df04cca37a559a74732cf3a861be62328d552ad5.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "aeb3142f0103c82fd4a928be9be5bd5618a598708307062d49523433db09ff3f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcfa024eca28447073ee5288899a7de7e044c214f0596bde29119b0f92ec72cb", "generation_seconds_batch": 25.625156878028065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9051170349121094, "target_z": 3.0000002204337455, "ce": 5.526196479797363, "genuineness": 4.7081804275512695, "identity": 0.6400607824325562, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aeb3142f0103c82fd4a928be9be5bd5618a598708307062d49523433db09ff3f.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "aed006137a6092b40620b8a652148d4dd2a2dd060fe9f5eb77c7c68095039677", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58c05bab57b4cf0dcf37599417f94f1b700f0d2885d09b22e5e8e82625e5ea59", "generation_seconds_batch": 17.013113211956806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8882172107696533, "target_z": 2.9687502101009136, "ce": 5.704906940460205, "genuineness": 4.7458367347717285, "identity": 0.7293893098831177, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/aed006137a6092b40620b8a652148d4dd2a2dd060fe9f5eb77c7c68095039677.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "af2e8263da47b3d7b823cf1dde3c72e162da0d1986a9496fb2efe81fcb6e7dc2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af236a275d973f575e9ac7ed4fe5e40c4d92f16668afd98817a2ea0fda765c31", "generation_seconds_batch": 21.510796525981277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.716308355331421, "target_z": 4.500000275542182, "ce": 4.966238498687744, "genuineness": 4.444586753845215, "identity": 0.7080433368682861, "hypothesis": "J'ai trouvé la petite boîte, elle était près de là elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.2631578947368421, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/af2e8263da47b3d7b823cf1dde3c72e162da0d1986a9496fb2efe81fcb6e7dc2.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "afe3232846c92408bcccdbd093352db7ae0232167a4ffa4c33a60ff0ddc94df6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f37f5edb09540b186cc5a9504c2c82a38ede9697290af162c6bfdf460684490", "generation_seconds_batch": 20.386862203013152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9191060066223145, "target_z": 4.874999958668673, "ce": 5.792276382446289, "genuineness": 4.6705241203308105, "identity": 0.43514591455459595, "hypothesis": "He encontrado. La cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/afe3232846c92408bcccdbd093352db7ae0232167a4ffa4c33a60ff0ddc94df6.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "b08f61c45d9af271f3b575a81b90a8470a75ee8b2b44c83e9a7c0be6d5d88a9f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ce8e9627479afcab32de7bb60db9220a6f4e08fb9d7da51ab127d36fe6ad8e0", "generation_seconds_batch": 20.95358872995712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 5.696964263916016, "genuineness": 4.507347106933594, "identity": 0.3721325397491455, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b08f61c45d9af271f3b575a81b90a8470a75ee8b2b44c83e9a7c0be6d5d88a9f.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "b0ddc5af38b21e906d2de79b61aeac395b5484599059cf41e1f81e2db312d3b2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e72ee64bcfc350496cdea899243e64b39041c0f9edc73a7a0971b3a52022318", "generation_seconds_batch": 22.810742693021894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5304102897644043, "target_z": 4.156250161881031, "ce": 6.078212261199951, "genuineness": 4.821148872375488, "identity": 0.6670773029327393, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b0ddc5af38b21e906d2de79b61aeac395b5484599059cf41e1f81e2db312d3b2.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "b2a44073f3775456cb9ba727ef22d72c90a562177f1bd1a7a484bc5f903c0082", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1faa63d8364a016e305e31e6fe6ee5c56b1565ee02b3455506476fc35238eb27", "generation_seconds_batch": 24.1766748779919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 6.117925643920898, "genuineness": 4.946669578552246, "identity": 0.751693069934845, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b2a44073f3775456cb9ba727ef22d72c90a562177f1bd1a7a484bc5f903c0082.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "b2e1e5af44e1f48e3f49db8512887bd5685ed95620f6729c4f0caaf18d9c2fb8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b87e375f01afe4276764c84dc3af9c42023a5a20210d6b12d99a0d6f4934084f", "generation_seconds_batch": 16.37485761300195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 5.403085231781006, "genuineness": 4.595211505889893, "identity": 0.8757420182228088, "hypothesis": "Ton message est arrivé après mon départ, je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi que nous pourrons parler.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b2e1e5af44e1f48e3f49db8512887bd5685ed95620f6729c4f0caaf18d9c2fb8.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "b35cf61bb34f80d1521a32ea97c10becf2b97fb6fffc77e927215b746ae4d3f0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "824a90879465ec7ef8a74433cde29fbfbd49d5c79be568bbb723afda099a328c", "generation_seconds_batch": 15.374547465937212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5473101139068604, "target_z": 4.187500172213864, "ce": 5.1628193855285645, "genuineness": 4.469690799713135, "identity": 0.626903235912323, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b35cf61bb34f80d1521a32ea97c10becf2b97fb6fffc77e927215b746ae4d3f0.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "b37ff2683e26ed1468f499d5dd4d06f4ee6d28aee899857351f973b96c66e36e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b6f08b953ffa6539a7a38cda877fafdc4cc6902404551b3eb04878f14ca7c2d", "generation_seconds_batch": 16.15437506500166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9558162689208984, "target_z": 3.0937498105647503, "ce": 5.752562999725342, "genuineness": 4.519899368286133, "identity": 0.6550965905189514, "hypothesis": "La puerta sigue abierta. He Nelos. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b37ff2683e26ed1468f499d5dd4d06f4ee6d28aee899857351f973b96c66e36e.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80ab0f5789c0db395b3d7e060cb428c2bb9661dce9d501d7383339bb650265c1", "generation_seconds_batch": 14.329132333979942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3226073384284973, "target_z": 0.07373045868625235, "ce": 6.229123115539551, "genuineness": 4.356721878051758, "identity": 0.5972476005554199, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "b4a3c4645749c347b7b73d2819a0a41711c5a9343e52ccb25d45676ce58e3499", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "72761f95c8ca3629c996e743ed6a5e866fdac7cf92c705b09867527ccc03381c", "generation_seconds_batch": 15.7739575849846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071204423904419, "target_z": 5.156250051664159, "ce": 5.283945083618164, "genuineness": 4.607763767242432, "identity": 0.3726446032524109, "hypothesis": "Non, j'ai troué la petite boîte. Elle était près de... près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b4a3c4645749c347b7b73d2819a0a41711c5a9343e52ccb25d45676ce58e3499.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "b4b85ba27dcbf75649ff22146f976a9eae2db1eca71aaebb7ea54b39815e46d2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7328562addef8ab417ad24084bccdffc49867b20fe4ccaabe833e2161312aad5", "generation_seconds_batch": 21.224961521918885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.217763662338257, "target_z": 3.5781251911573886, "ce": 5.764476776123047, "genuineness": 4.3881025314331055, "identity": 0.4440501928329468, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekkast. We zetten het naar de lunch terug.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b4b85ba27dcbf75649ff22146f976a9eae2db1eca71aaebb7ea54b39815e46d2.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "b4e668330307da1ea83ac3b8846792a1cfba3054c14a9698b5535143748a131a", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8183d8c370f278290587494138a53bdd0836e86e52b022e89f3f9f631f84ba70", "generation_seconds_batch": 21.261358318966813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.155703544616699, "target_z": 5.312500103328318, "ce": 5.839932441711426, "genuineness": 4.68307638168335, "identity": 0.7957032322883606, "hypothesis": "Dans mes sage est arrivé après mon départ. Je l'ai relue et puis... J'ai rangé mon téléphone. Dis-moi quand nous pouvons parler.", "wer": 0.2857142857142857, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b4e668330307da1ea83ac3b8846792a1cfba3054c14a9698b5535143748a131a.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "b51da38b7816cad1e70fdf3a55232364f6377f98c66c6d6bd8b3b58c820a728d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4c75eac33df95b9fd7002e75b2b2ccfacba17696fafbc80a3b13591803e0ee8", "generation_seconds_batch": 16.097745296079665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6347198486328125, "target_z": 2.5000000551084365, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.6694989204406738, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b51da38b7816cad1e70fdf3a55232364f6377f98c66c6d6bd8b3b58c820a728d.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "b52fa39044e0c536af64c2dafcabdf198097dd97b4239080804c043cc2644fd0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3d664045c9bf0cf09ab3f68a8da4761f663c91930d65b3e33f475b3607edde5", "generation_seconds_batch": 22.848197911982425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.338973045349121, "target_z": 1.9531250947176249, "ce": 5.927301406860352, "genuineness": 4.8588056564331055, "identity": 0.756230890750885, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b52fa39044e0c536af64c2dafcabdf198097dd97b4239080804c043cc2644fd0.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "b5dedf41c475e6c840dc55ff6b6d41222221ca0db48263e78afbaea4451c2122", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b19326cab0fbdad355febe67739f2d2366b8a04d9ca152b25a9c5c5497a5e458", "generation_seconds_batch": 20.606988786021248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0572152137756348, "target_z": 3.281249872561741, "ce": 5.035736560821533, "genuineness": 4.293961524963379, "identity": 0.6750763654708862, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b5dedf41c475e6c840dc55ff6b6d41222221ca0db48263e78afbaea4451c2122.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "b69da2d898af2281ddafc3455ecbb614172f63ac0bc7da8663bed3b835104338", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3af6c0c65f00bc6d868dcbbfb723c2b7512a5eb25a40e56123f7a380e31ee41", "generation_seconds_batch": 15.603769718902186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.341601610183716, "target_z": 5.656250216989468, "ce": 5.506340026855469, "genuineness": 4.557555198669434, "identity": 0.8401914834976196, "hypothesis": "Oh la route tourne à gauche après bon continue jusqu'à la petite barrière en bois Je t'attendrai de l'autre côté", "wer": 0.15, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b69da2d898af2281ddafc3455ecbb614172f63ac0bc7da8663bed3b835104338.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "b6d49cbd79db850c5be26dd2f0e491ab899267833ac884c94d8d2a8485e8769e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7404c5992af0ee0b4149ccac934c40d5b39ebbda0dc06fc85491897c5b856c1", "generation_seconds_batch": 20.277096166973934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0065157413482666, "target_z": 3.1874998415632456, "ce": 5.101263999938965, "genuineness": 4.582659721374512, "identity": 0.7271410822868347, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b6d49cbd79db850c5be26dd2f0e491ab899267833ac884c94d8d2a8485e8769e.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "b6eb4c660e5ce5bdabb1f258b3eb930c3bfaacbd3d67750738ab05788c9e0319", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25d281dffa859b12cdeeff37f87bd38c4396da850a745a6b9a3f255ea739f2cd", "generation_seconds_batch": 20.77002086106222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.250248908996582, "target_z": 1.7890624302533853, "ce": 5.744620323181152, "genuineness": 4.6956281661987305, "identity": 0.742477297782898, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b6eb4c660e5ce5bdabb1f258b3eb930c3bfaacbd3d67750738ab05788c9e0319.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "b731b8d57420b7961d04ffff623b75595335d9bdff7ff427388839e0fbfe8120", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ad1d5f67fd162221d3667d2ee324df066731bd5a0f894d3d7ed6045b956c12a", "generation_seconds_batch": 18.987727724947035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5105998516082764, "target_z": 5.9687503203177865, "ce": 5.089349746704102, "genuineness": 4.099404335021973, "identity": 0.38011419773101807, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b731b8d57420b7961d04ffff623b75595335d9bdff7ff427388839e0fbfe8120.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "b7a5da60a0b5fffd688e53e7550769c88dfdd1fbdf54f300ad5ec49b4e91ed93", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0378a023320aa8dce94847154b9208702b51dfd0faf57af9a5a431ef96c78f34", "generation_seconds_batch": 15.420629209955223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.285362958908081, "target_z": 3.703125232488716, "ce": 5.772419452667236, "genuineness": 4.758388519287109, "identity": 0.8223975896835327, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b7a5da60a0b5fffd688e53e7550769c88dfdd1fbdf54f300ad5ec49b4e91ed93.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "b7cacd46047033fd5c1ce1c5ee41a9dcf4fca8b0a5ef8f607ba9a505e1954b37", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2419e4f6b0fc7d4c019c641a2238e6dc2bbfeed2f9cbf4a51709556f73ca5a82", "generation_seconds_batch": 22.554253038018942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3178482055664062, "target_z": 1.9140624715847125, "ce": 6.109982967376709, "genuineness": 4.6956281661987305, "identity": 0.7725049257278442, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b7cacd46047033fd5c1ce1c5ee41a9dcf4fca8b0a5ef8f607ba9a505e1954b37.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "b87d547302e87b863910be85e859dc8a381bc131451c38b0aada3eb4841ba221", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8703dfc9f0172dfc76246a06b376357de7d5684d75b00d215e6cded4c941bdc", "generation_seconds_batch": 16.290968342102133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.443000555038452, "target_z": 5.843750278986459, "ce": 5.649308204650879, "genuineness": 4.494794845581055, "identity": 0.6866438388824463, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b87d547302e87b863910be85e859dc8a381bc131451c38b0aada3eb4841ba221.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "b8d330d7303d910bdeb80884d277effd760f7b21749c0546c90cdcc6570b23fa", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb08efa2fd3eebaab485a36d558d9b7de16b1cbdd318cba7c73c289c1ce2d5d9", "generation_seconds_batch": 20.65303165500518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5612990856170654, "target_z": 6.062499910448791, "ce": 5.434855937957764, "genuineness": 4.595211505889893, "identity": 0.6674723625183105, "hypothesis": "Ma route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b8d330d7303d910bdeb80884d277effd760f7b21749c0546c90cdcc6570b23fa.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "b906ebf5bd8aa859f52a675e528eddfd022e3a7f19071ef305bf3ceed641afa6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6ebafdb516cb0c8327e8eaaa3bf7f785e5a9c0559604bd21f34d2126128fe6f5", "generation_seconds_batch": 22.831985929980874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9360058307647705, "target_z": 4.906249969001505, "ce": 5.669164657592773, "genuineness": 4.7081804275512695, "identity": 0.599926769733429, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b906ebf5bd8aa859f52a675e528eddfd022e3a7f19071ef305bf3ceed641afa6.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "b94af1d698611fad76c45f600d3a65bdeae30cdf9e1b8b4907ccac9ca163138b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd15fd69d0540896f814223f59066818022619adc79df37cd361c87a8484058d", "generation_seconds_batch": 15.244958297000267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.305173397064209, "target_z": 1.8906250740519612, "ce": 6.022613525390625, "genuineness": 4.7834930419921875, "identity": 0.8524550795555115, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b94af1d698611fad76c45f600d3a65bdeae30cdf9e1b8b4907ccac9ca163138b.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "b99857d25d706738b8afce90e462dedc680fed33f2fbbc4b5b7f5e8a39d9f82c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "36b8ea3c0d0972f9e94fcc09a58134362d605640fc4c9b7fff6e0f1b659a92ce", "generation_seconds_batch": 21.10306962998584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6460804343223572, "target_z": 0.6718750017221387, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.6625277996063232, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/b99857d25d706738b8afce90e462dedc680fed33f2fbbc4b5b7f5e8a39d9f82c.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "ba21e2c2af2954b7989fca5f4160e5f244b56bf78ae7b1f022782f908a7d37da", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f81a0d4ccd9307cd096f955cd3aa08a70ef5f62aa6ddfda47622014ba28e48e", "generation_seconds_batch": 21.411917366087437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5552439093589783, "target_z": 0.5039062512916039, "ce": 6.181467056274414, "genuineness": 4.607763767242432, "identity": 0.674074649810791, "hypothesis": "La porte est encore ouverte. J'ai posé ton ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ba21e2c2af2954b7989fca5f4160e5f244b56bf78ae7b1f022782f908a7d37da.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de748f83f45c01df28bf2a33988bf1c2dc2c6e829a258c7099877009c6cf8125", "generation_seconds_batch": 17.22775938094128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0894426554441452, "target_z": -0.3574218829648912, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.8168303370475769, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les, quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "bad5cc626c998aaf684697c18c788a80fe011f0609c4b57d7957048a58093d83", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c2929bf4702a64565da63ed10a741072c0bda15f40232d236589025983d840a", "generation_seconds_batch": 22.10846312204376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1839640140533447, "target_z": 3.5156251704917247, "ce": 5.959072113037109, "genuineness": 4.400654315948486, "identity": 0.4847901463508606, "hypothesis": "Ik heb het kleine doosje gevonden en het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bad5cc626c998aaf684697c18c788a80fe011f0609c4b57d7957048a58093d83.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "bb6a2aaad533842d015575ca38ee957ba51fd2a1a91d9493b2ef7601d13d3667", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0608a25b4f30e66d69d2cf0c4edd93b24f778a1c1d69431faccfeb8393cbe32f", "generation_seconds_batch": 22.757690811995417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.124814510345459, "target_z": 3.406249913893068, "ce": 5.216432571411133, "genuineness": 4.607763767242432, "identity": 0.6429858803749084, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bb6a2aaad533842d015575ca38ee957ba51fd2a1a91d9493b2ef7601d13d3667.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "bb74dc95f6eeb6831d2f242420e361638d272dbf86480d4aec0f402c16cae72c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "731388f6ee49931b02e0dd183c44e6ea9a54fba30e3413d1b409e0c41d49b819", "generation_seconds_batch": 15.48974129196722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.155703544616699, "target_z": 5.312500103328318, "ce": 5.546053409576416, "genuineness": 4.086852550506592, "identity": 0.3461832106113434, "hypothesis": "De sleutels liggen op de keukentafel en keken in de la. En daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bb74dc95f6eeb6831d2f242420e361638d272dbf86480d4aec0f402c16cae72c.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "bba7734e18dfb131501edd2c0d46ba3fedffad289e5a930c39d740d28d0d81f0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7edb89fe133470e7b0e57295522886ae43fbebbf309f4fa0d5909e24a02fed01", "generation_seconds_batch": 23.26229542598594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6516196727752686, "target_z": 2.531250065441268, "ce": 5.935244083404541, "genuineness": 4.432034492492676, "identity": 0.5083450078964233, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bba7734e18dfb131501edd2c0d46ba3fedffad289e5a930c39d740d28d0d81f0.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "bbbdca3ac7b7073c99daf4037d361069f4f683aa82648fe059cf87d7ef79a024", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf11a5b8f3b67a2e95b08b67837a8cc01c1d04d0f8a8bb88f987f55146b304bf", "generation_seconds_batch": 15.689396557048894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 5.498397350311279, "genuineness": 4.833701133728027, "identity": 0.8411476612091064, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bbbdca3ac7b7073c99daf4037d361069f4f683aa82648fe059cf87d7ef79a024.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "bbcea7813d558d77ce3be713cce492abe8ad31cac42009f91a0a88a31d571caa", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "56ec11d5d8079da041e703c64a1f2003877b48c6eb0fd8b93c0fd4781543e68f", "generation_seconds_batch": 16.501798779005185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2093136310577393, "target_z": 3.5624999655572274, "ce": 5.871703147888184, "genuineness": 4.545003414154053, "identity": 0.33059167861938477, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers, bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bbcea7813d558d77ce3be713cce492abe8ad31cac42009f91a0a88a31d571caa.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "bc1b5e84032db49d53f77da0216b7a1438510db8f7a105384cac270b0867f060", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45566bfcb7a1c3ae5acefec03d819da40f3a4d50aba7f32a9c5bf3bf06c58655", "generation_seconds_batch": 21.10306962998584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.831978440284729, "target_z": 1.015625005166416, "ce": 5.95112943649292, "genuineness": 4.356721878051758, "identity": 0.5192356109619141, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bc1b5e84032db49d53f77da0216b7a1438510db8f7a105384cac270b0867f060.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "bc4f2dfacbd0046ad93578c1e16d51ad50a551c9da5bf6840977a9fc1a88321b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd75d4ef4b868872159defc295f670483d646d34365bb0d628566d4df857e317", "generation_seconds_batch": 18.987727724947035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4768002033233643, "target_z": 5.906250299652123, "ce": 5.450741291046143, "genuineness": 4.250029563903809, "identity": 0.48245811462402344, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bc4f2dfacbd0046ad93578c1e16d51ad50a551c9da5bf6840977a9fc1a88321b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "bc76150e12416c08e27e007cf55d0f9ee0cfb184539e6a62ac0e7b5fe1142c0c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ed2b7e12fc78ca187308573c334b22695ef2a8d9be7b1b30dcc8f41bb3746ba", "generation_seconds_batch": 23.73468866501935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5502207279205322, "target_z": 2.3437500034442773, "ce": 5.331601142883301, "genuineness": 4.645420074462891, "identity": 0.7057308554649353, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bc76150e12416c08e27e007cf55d0f9ee0cfb184539e6a62ac0e7b5fe1142c0c.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "bc819de01acf0befbcccc1738d000016ffb772db8c7873df57bd293674edd51d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c6e670ef833e932c06b8fd6b233dc59ee8295125c17097f1ea1561a2c244ad7", "generation_seconds_batch": 16.046483009005897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29171237349510193, "target_z": 0.01660158176642598, "ce": 6.062326908111572, "genuineness": 4.68307638168335, "identity": 0.6828863024711609, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bc819de01acf0befbcccc1738d000016ffb772db8c7873df57bd293674edd51d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "bccb3ff55aa03db639d104e59edd782e736030fe5f5c98ddc497d935469521a0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cc15277582ecd8f69db353ef28ed5826d01de14dca74b677c64d20cc2a33374", "generation_seconds_batch": 21.296912563033402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4910714626312256, "target_z": 2.2343751877131113, "ce": 6.252951145172119, "genuineness": 4.796044826507568, "identity": 0.39401981234550476, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bccb3ff55aa03db639d104e59edd782e736030fe5f5c98ddc497d935469521a0.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "bd6d9bb159983c5f83bee998c6787acfc0fcf688568369187279e6a3b139295b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f23e7b696069c74fa4d7f73e7c56cbbe45bde159ce1bcb5fd3c2b9ade329c17d", "generation_seconds_batch": 16.566924044047482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7517043352127075, "target_z": 0.8671875663023374, "ce": 6.229123115539551, "genuineness": 4.65797233581543, "identity": 0.6159011721611023, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bd6d9bb159983c5f83bee998c6787acfc0fcf688568369187279e6a3b139295b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "bdc5d1ddaca473ed79782e6714bd9d02f54622d63df1cfed66ccecb871a5b3a1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3dd3576bce9bdbda53a087c954d9be1aafd7702d428c93eaabab4b8a798dd614", "generation_seconds_batch": 21.739978451048955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.392301082611084, "target_z": 5.7500002479879635, "ce": 4.895747184753418, "genuineness": 4.356721878051758, "identity": 0.6198437809944153, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bdc5d1ddaca473ed79782e6714bd9d02f54622d63df1cfed66ccecb871a5b3a1.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "be302fcfe1fa925a60156832b2d32466ab29eb53d5258bfec707c1a9423d549a", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7df61817d45e369c2cdf8a004238667ef200e3d334d7c648ff7425cecba167fc", "generation_seconds_batch": 16.905436469009146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6457982063293457, "target_z": 6.21874996211295, "ce": 5.577824115753174, "genuineness": 4.532451152801514, "identity": 0.37851810455322266, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de laag en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/be302fcfe1fa925a60156832b2d32466ab29eb53d5258bfec707c1a9423d549a.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "bf24c7b9f1f39e688842da146aac388320911cd8b52e34a7dfa0e19234d496da", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2946de8163b6ed5bf427dcd5350920e0fc7245518cfc1f6e7ea5cf023e37e2eb", "generation_seconds_batch": 20.928502753959037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5304102897644043, "target_z": 4.156250161881031, "ce": 5.041693687438965, "genuineness": 4.457139015197754, "identity": 0.5523937344551086, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bf24c7b9f1f39e688842da146aac388320911cd8b52e34a7dfa0e19234d496da.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "bf326b0b77a4395c3339f008a07a6bb0ddcd67358e6a51b95ebeefb2f0d4b93c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5375e2cc47b65e25d314764cb224c36111335ae26f493f8ee2b130d66d961c8", "generation_seconds_batch": 21.672368922969326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.786818265914917, "target_z": 2.7812501481039225, "ce": 5.649308204650879, "genuineness": 4.218649387359619, "identity": 0.7508635520935059, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bf326b0b77a4395c3339f008a07a6bb0ddcd67358e6a51b95ebeefb2f0d4b93c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "bf4c71caea29c7c116db87a9a5b99153677c010d395d7eb2d5f8444cc27d1ed9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c6fab493b1c68d15b798ef4eb7fa518b2692c65c9611e61d6ff597006bc16c4", "generation_seconds_batch": 21.04456470499281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.319162607192993, "target_z": 3.7656252531543792, "ce": 4.912625312805176, "genuineness": 4.344170093536377, "identity": 0.7590556144714355, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bf4c71caea29c7c116db87a9a5b99153677c010d395d7eb2d5f8444cc27d1ed9.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "bf77ee81f01e4408d7c7537c904147295d30f9d96ad21d4f2d1469ef7a7188c5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8511a51473bf630bb1f7e431c54e7929391a27ac2aa79504588f3474604a72e", "generation_seconds_batch": 23.1543828350259, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14912013709545135, "target_z": -0.24707032530840609, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.40595880150794983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bf77ee81f01e4408d7c7537c904147295d30f9d96ad21d4f2d1469ef7a7188c5.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "bfebdba28a796105fac0d982f2918df6750ab595ce1f4c7d1a105122c05e9e7e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66fef9f35d3f25c18bc2a1c9781a59ba866025dc926f00cfb7f45668047f578a", "generation_seconds_batch": 16.950407529016957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2262134552001953, "target_z": 3.5937499758900593, "ce": 6.0305562019348145, "genuineness": 4.557555198669434, "identity": 0.2876819372177124, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/bfebdba28a796105fac0d982f2918df6750ab595ce1f4c7d1a105122c05e9e7e.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "c05a5e948479918565bdca4507a14a9f77b6cdbfd796f5fdb4a20931aae6d627", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c0a5b1e6030edc4339e4760e94581f8761e7b472da4be617eec5d931946eb4c", "generation_seconds_batch": 22.976312109967694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.217763662338257, "target_z": 3.5781251911573886, "ce": 5.95112943649292, "genuineness": 4.7332844734191895, "identity": 0.7896668910980225, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c05a5e948479918565bdca4507a14a9f77b6cdbfd796f5fdb4a20931aae6d627.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "c21849198712f0ab4b395e480dde03e4dede83b31e0b1109a958103b6af9b615", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb03bc81113ab6a026fd1218bd8890b9fb06346db0fa0e719314ede6095ee5d3", "generation_seconds_batch": 16.855339369969442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.10209321975708, "target_z": 7.062499800231918, "ce": 5.5817952156066895, "genuineness": 4.193545341491699, "identity": 0.04443105310201645, "hypothesis": "De weg gaat er linksaf naar de brug. Loop verder tot aan het kleine auto hek. Ik wacht aan de andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c21849198712f0ab4b395e480dde03e4dede83b31e0b1109a958103b6af9b615.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "c281c6ef59addfb5af170068cafd8686531fe0c63634042ac98093a8e0edbc9f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c77b30722e257ab329266c5642b0a001fe67db655e78359c81bc97aa86369ed9", "generation_seconds_batch": 15.866516322013922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6656088829040527, "target_z": 4.406250244543686, "ce": 5.5539960861206055, "genuineness": 4.494794845581055, "identity": 0.6312363147735596, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c281c6ef59addfb5af170068cafd8686531fe0c63634042ac98093a8e0edbc9f.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "c35407d73accdacb045eeb6fe36ca9de41e2425d0500ffd02c11dccf9e6ebaaf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d57d77d4b8b749190ec4b8dfa21ebcebb78c8eef0c7aacb482f3635cef18ab62", "generation_seconds_batch": 21.655887729953974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.682508707046509, "target_z": 4.437500254876518, "ce": 5.935244083404541, "genuineness": 4.532451152801514, "identity": 0.3284820020198822, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c35407d73accdacb045eeb6fe36ca9de41e2425d0500ffd02c11dccf9e6ebaaf.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c35c365c4107c24d51435b4860623120762226207b828015abeafa02af5499ea", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04396ef4bae620f1ffccc00b815a1911802858c3ae10b2705babc26b328f79ec", "generation_seconds_batch": 14.888574691955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7614684104919434, "target_z": 2.7343749121709298, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.5430507659912109, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c35c365c4107c24d51435b4860623120762226207b828015abeafa02af5499ea.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "999ad97e6df4c9b60258b4c0b39191c93a6e75280e5d1c375fcb8fa0cc57954a", "generation_seconds_batch": 13.602856416953728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3820207715034485, "target_z": 0.18359375559695057, "ce": 6.221180438995361, "genuineness": 4.582659721374512, "identity": 0.7474506497383118, "hypothesis": "La carretera gira a la izquierda tras el puente. Te sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "c3ac0f400dbadd700d49f6f0b32509596e3c8fd160a7cd472e9640c53e70ce1f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72e7a96f8f21807a897a8eabbd7afbf8f5835a70ebd0295f2e9a230f38bb07aa", "generation_seconds_batch": 18.650135956006125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6516196727752686, "target_z": 2.531250065441268, "ce": 5.692992687225342, "genuineness": 4.632867813110352, "identity": 0.7159996032714844, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c3ac0f400dbadd700d49f6f0b32509596e3c8fd160a7cd472e9640c53e70ce1f.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "c4176c93c9b720e87dca508c9a4cd64da2d01260f7185f5cb58b6dde7a856a8f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1e6b1a9db96ba282ed841e1e916e8200b486a49767de551edda756779efe84b", "generation_seconds_batch": 24.715185934095643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3276124000549316, "target_z": 3.78125003788705, "ce": 5.982900142669678, "genuineness": 4.570107460021973, "identity": 0.6440305709838867, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c4176c93c9b720e87dca508c9a4cd64da2d01260f7185f5cb58b6dde7a856a8f.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c4245e751bf27e03f9180f13a52d549d8f664879af980ede43a9db8dd98f0f78", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5757b2e9bab20ba821a4e494a95361bcd1ee59b4e58834916b3fd45b3e68f1e", "generation_seconds_batch": 24.348458276013844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.288273572921753, "target_z": 1.8593750637191295, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.4202972948551178, "hypothesis": "Someone moved a little blue chair. It used to stand here beside the tall bookshelf. Now we can put it back after lunch.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c4245e751bf27e03f9180f13a52d549d8f664879af980ede43a9db8dd98f0f78.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "c44be29978b5bc750293c866f28c48e82def17412228dbbd6d5db3edd75391e0", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5abf5c2e20538da56d77640f220426bf60b617f2fa008eeec41f058e78cff7ee", "generation_seconds_batch": 15.75637153792195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1895031929016113, "target_z": 5.375000123993981, "ce": 5.403085231781006, "genuineness": 4.595211505889893, "identity": 0.7148109674453735, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón. Y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c44be29978b5bc750293c866f28c48e82def17412228dbbd6d5db3edd75391e0.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "c457b130aad194898b180204b6c33f2e4647326ba2323ed3d9587c69f6d9eb1b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57d7ee8ec390e2980819f887397723b6d8db0c64eb1dfc9bf6f085ef394fdc5f", "generation_seconds_batch": 16.469337180955335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9220166206359863, "target_z": 3.0312497898990864, "ce": 5.645336627960205, "genuineness": 4.7081804275512695, "identity": 0.8473564386367798, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c457b130aad194898b180204b6c33f2e4647326ba2323ed3d9587c69f6d9eb1b.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b33522133c7d9399bafba0127dd193c567ee6d66e7aa583d5ed6c32a5d8d8c81", "generation_seconds_batch": 14.036032180069014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7263545989990234, "target_z": 0.8203125508030897, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.6288763880729675, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "c5d8e847089a97525c27178c6d367a538f79c8b6db952e41d4dc16b92783d1d2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0cf65a9dd79582bcb31d667e83892987fa360e862744198c8be4d0fcadb08c5", "generation_seconds_batch": 21.261358318966813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.088104248046875, "target_z": 5.187500061996991, "ce": 5.498397350311279, "genuineness": 4.6705241203308105, "identity": 0.6477270126342773, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu. Puis j'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c5d8e847089a97525c27178c6d367a538f79c8b6db952e41d4dc16b92783d1d2.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "c639f93bf5e42ecf75b1bb8ef8e83df9fc36b8d40cc9da0d3669a49a3aee1227", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f91a51cba4319326b7648f8a928b501ea922225e5373db90bb9a21466c1f57ee", "generation_seconds_batch": 23.325945831020363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20615702867507935, "target_z": -0.1416015679893169, "ce": 6.395919322967529, "genuineness": 4.519899368286133, "identity": 0.5996477007865906, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c639f93bf5e42ecf75b1bb8ef8e83df9fc36b8d40cc9da0d3669a49a3aee1227.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "c67ba2e9f2f743821e39acb56125ff919f34ea85c7314000e1d6bf52f0f8c34b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "949e776525db9500ea7da5ea3e48da2e0176de00997014f9501e6b1710121b5e", "generation_seconds_batch": 16.126924780081026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.192413806915283, "target_z": 3.5312499552243954, "ce": 5.355429172515869, "genuineness": 4.3504462242126465, "identity": 0.5524085760116577, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c67ba2e9f2f743821e39acb56125ff919f34ea85c7314000e1d6bf52f0f8c34b.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "c6dc6a35f7de8973661b2e1c0d3cdc204dbc2bdcd28a062bb032090cefef9961", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6495ba3c15d111b7f083ba599fb5cef795d5b4aefeb7174bc17f8c08bb2e6608", "generation_seconds_batch": 22.45931399310939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.496610641479492, "target_z": 4.093750141215368, "ce": 5.855817794799805, "genuineness": 4.362998008728027, "identity": 0.44872909784317017, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c6dc6a35f7de8973661b2e1c0d3cdc204dbc2bdcd28a062bb032090cefef9961.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "c7b3d95546f8a85642779aa70b5ea82325025f7a15974cc3ace56386d458a802", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6e1def3d17c9a65ce322e35da6fc032b16d275eeb8bf0fa8a52a1fee8d8e800", "generation_seconds_batch": 23.77611587406136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8024037480354309, "target_z": 0.9609374870839602, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.27280154824256897, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c7b3d95546f8a85642779aa70b5ea82325025f7a15974cc3ace56386d458a802.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a29ae7829eaa4545e51cdea97d9fd55ee2c878c7a0c69b8ec4054f9e0f3d675", "generation_seconds_batch": 16.236490941955708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0009765625, "target_z": 1.3281248880609888, "ce": 6.260893821716309, "genuineness": 4.432034492492676, "identity": 0.8072153329849243, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "c824dbaf5b39cc812776aac76270e2362098200833fb424564e42935bcb1a416", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4aac687ebd1feab05e0a7d0737bf199de66e6860b60af0674e695eb3e964fe2", "generation_seconds_batch": 20.519363917061128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7179046869277954, "target_z": 0.8046875456366738, "ce": 5.780362129211426, "genuineness": 4.6203155517578125, "identity": 0.7816447019577026, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c824dbaf5b39cc812776aac76270e2362098200833fb424564e42935bcb1a416.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "c83181e7820bc7ce0fc3a508efda761ce02afa3c18bbe1fb0ab1dbde5efceaa9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "158805d8be6dd1942fae8277955092dbc58f3b365f3df42ad353d9781b01c887", "generation_seconds_batch": 14.883724287967198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3566710352897644, "target_z": 0.13671874009770285, "ce": 6.125868320465088, "genuineness": 4.080576419830322, "identity": 0.4461144804954529, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c83181e7820bc7ce0fc3a508efda761ce02afa3c18bbe1fb0ab1dbde5efceaa9.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c83522ed7367b96248284ceee224bf65282eff8847de7182ce76bf85294564d3", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae54a89fd7a711df9e54c31e29d1e42fe1e4e4f757b951a95a17d4e1177469d5", "generation_seconds_batch": 16.87762774399016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8713173866271973, "target_z": 2.9375001997680816, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.1786092221736908, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after long.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c83522ed7367b96248284ceee224bf65282eff8847de7182ce76bf85294564d3.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "c8419b5c137199429dd6494af532473f3d4b63c37ecbe6334a903969080276b6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "156fd22a0245c74702a03732da284ea514a576fdfb9374832eb0d2c3053136f7", "generation_seconds_batch": 22.55927092989441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2431132793426514, "target_z": 3.6249999862228908, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.46032801270484924, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c8419b5c137199429dd6494af532473f3d4b63c37ecbe6334a903969080276b6.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "c844bc6c07c09babc1ad79117059a87cba3afbd121b0b0fed8b57226891b9ff8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cce5348fbaf9b62a4a28aaded89445479efcdf861dbdfcb1451808c64fdadd78", "generation_seconds_batch": 14.09338602796197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6093699932098389, "target_z": 2.4531248191754433, "ce": 5.530168056488037, "genuineness": 4.017816066741943, "identity": 0.4516580402851105, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c844bc6c07c09babc1ad79117059a87cba3afbd121b0b0fed8b57226891b9ff8.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c31c692d3f85ad31e2ce412080489ba57e5759b42d1461792a7300c3512cf8e", "generation_seconds_batch": 17.20113930304069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20193207263946533, "target_z": -0.14941407057252484, "ce": 6.348263263702393, "genuineness": 4.3881025314331055, "identity": 0.17285843193531036, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "c8b608874f79858a0f38eb1c3de98c71445fe478a3f116a6c0ab800c37424cf4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eaff392d59047187708908d174458150dee5cca231a37fe5c72cb204149cf605", "generation_seconds_batch": 22.579855468007736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8108536601066589, "target_z": 0.9765624922503762, "ce": 6.348263263702393, "genuineness": 4.846253395080566, "identity": 0.367898553609848, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c8b608874f79858a0f38eb1c3de98c71445fe478a3f116a6c0ab800c37424cf4.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "c8d7d00f486982036f9994b58cc58de70679d713d8835d4740673c3be03c488e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb15f43d5097152b28e6e2cabb3da533646c362764ba5ec4da2ce681893eb406", "generation_seconds_batch": 21.926476173917763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3178482055664062, "target_z": 1.9140624715847125, "ce": 5.967014789581299, "genuineness": 4.7081804275512695, "identity": 0.7869080305099487, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c8d7d00f486982036f9994b58cc58de70679d713d8835d4740673c3be03c488e.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "c9897320a7becd0d7d7bddbf48412ca7316678debd8cd55d76eeb3fcab50b115", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "57616ae1b4e6ea5026961da4c740568d22c8c11d13cf66510a87e5f664abee2f", "generation_seconds_batch": 20.606988786021248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6626980304718018, "target_z": 6.2499999724457815, "ce": 4.497620582580566, "genuineness": 4.256305694580078, "identity": 0.62646484375, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c9897320a7becd0d7d7bddbf48412ca7316678debd8cd55d76eeb3fcab50b115.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "c9ae438212df427694da4e2a1e7e331c06530bba55c7af07f748efac28a9ea8e", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78ccebbbc7054e5b5627be3bf1b030140e58b44572c9ec7aecb466be4693a88e", "generation_seconds_batch": 18.650135956006125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9698054790496826, "target_z": 4.9687499896671685, "ce": 5.657250881195068, "genuineness": 4.7834930419921875, "identity": 0.7966585755348206, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/c9ae438212df427694da4e2a1e7e331c06530bba55c7af07f748efac28a9ea8e.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "ca48e0375e40bf59b8e4ff38234744053fb78975fb74399ff3f652675cd07efe", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50920f92bc72190b0b09724e2a1d34d5d55873c8e55a8825a2ab83594873d384", "generation_seconds_batch": 21.464500084053725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4150221347808838, "target_z": 2.093749920781623, "ce": 5.998785495758057, "genuineness": 4.946669578552246, "identity": 0.6938295364379883, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ca48e0375e40bf59b8e4ff38234744053fb78975fb74399ff3f652675cd07efe.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "caa066d910f55c1d62e4153eccaabc23238eaaacbe754dd36e065af98b99cd27", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fba10ee0c8a7e8b85a56da19f1b4681eaf3cf2162beb6fe661f345a6378bfd5b", "generation_seconds_batch": 21.269782681949437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5304102897644043, "target_z": 4.156250161881031, "ce": 5.462655067443848, "genuineness": 4.482243061065674, "identity": 0.6901691555976868, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/caa066d910f55c1d62e4153eccaabc23238eaaacbe754dd36e065af98b99cd27.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "caa6ae5ca8dbb49b333cb67ca40be94d9703926b8b52c501778baf67e2905673", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef585acfe8cfbdaa61a407b2bba9edfd573f0501894efebfdbe9f7ee031d9614", "generation_seconds_batch": 22.346747720032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9291523694992065, "target_z": 1.1953124543633262, "ce": 6.141753673553467, "genuineness": 4.557555198669434, "identity": 0.3604399859905243, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/caa6ae5ca8dbb49b333cb67ca40be94d9703926b8b52c501778baf67e2905673.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "cb08aeecd72533b6e7f0c9c752f423316259b6fc23d9afdadd10fcd3b5332bfc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c35bfbecb69ca3f698f79f5e0e2ae45730eaa20df0a61f388d94f62be34a5533", "generation_seconds_batch": 21.02740719600115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6854193210601807, "target_z": 2.593750086106932, "ce": 6.300607204437256, "genuineness": 5.034534454345703, "identity": 0.691597580909729, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cb08aeecd72533b6e7f0c9c752f423316259b6fc23d9afdadd10fcd3b5332bfc.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "cb341b911980de7960fba6d213a664e5d86a2728c29be3f93e001ba5111e74fb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0137c8771aa00c339e42daa2b03057f03fe50acfefe0cb9db31d417789417f65", "generation_seconds_batch": 21.601922195055522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9220166206359863, "target_z": 3.0312497898990864, "ce": 6.006728172302246, "genuineness": 4.758388519287109, "identity": 0.6861444711685181, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cb341b911980de7960fba6d213a664e5d86a2728c29be3f93e001ba5111e74fb.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "cbbc9d4c95d43b8e949adfcd6fa8ea96c1dc196ec009e6c7ec7e318c55c5ad8d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b0461eb2bd9ed2eb7cf5ef806caf5c8e06b2f07b6430d3fc0c0bacdae573bf9", "generation_seconds_batch": 20.898452191031538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6798800826072693, "target_z": 0.7343750223878023, "ce": 6.117925643920898, "genuineness": 3.948779582977295, "identity": 0.32647794485092163, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cbbc9d4c95d43b8e949adfcd6fa8ea96c1dc196ec009e6c7ec7e318c55c5ad8d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "cbca0e6a4876edeacecc8b92c99461ab1a257324eb58b21408f492b53636cd77", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c752dbbe9959fe7311a18827e2f64cbb3fe8ad0edb2f789e3939bc4bbd196a1", "generation_seconds_batch": 14.841357325902209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8024037480354309, "target_z": 0.9609374870839602, "ce": 6.181467056274414, "genuineness": 4.413206577301025, "identity": 0.3265141248703003, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cbca0e6a4876edeacecc8b92c99461ab1a257324eb58b21408f492b53636cd77.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "cbf37b7ab91bbf5bf664c0287f09f230d04e8fa162eac6459cc1b232575cf266", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b307f558b662705ac077b29e0caa3f97afe8b0729292e5013b06865d9463110d", "generation_seconds_batch": 14.844384640920907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18239165842533112, "target_z": -0.18554688124275256, "ce": 6.38797664642334, "genuineness": 4.68307638168335, "identity": 0.612949013710022, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cbf37b7ab91bbf5bf664c0287f09f230d04e8fa162eac6459cc1b232575cf266.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "cc035b3296f849f5729a682f8d9e55bafa71167ddd3102eeecdd4c92b9e27968", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd532353d4308ed274dfad7aa707c11c46a2f76db49baf6f27add2389592852d", "generation_seconds_batch": 17.79698585299775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 5.260117053985596, "genuineness": 4.2374773025512695, "identity": 0.7331715822219849, "hypothesis": "La route tourne à gauche après le pont continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cc035b3296f849f5729a682f8d9e55bafa71167ddd3102eeecdd4c92b9e27968.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "cc53b5047f388e7715b582d248b26554c27d617212e71c3c219e6b0f8c327407", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e9a4b8f7a70aead9566d3f16ca22dbb549644395e65d9203c4eb3c4d74ce096", "generation_seconds_batch": 20.69661540305242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7952680587768555, "target_z": 2.796874932836593, "ce": 6.324435234069824, "genuineness": 4.821148872375488, "identity": 0.5537806749343872, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cc53b5047f388e7715b582d248b26554c27d617212e71c3c219e6b0f8c327407.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "cc636aa151bf873906d3933099af990ff85e0acb1206968ee2a29cdf69e4c7af", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70f2a71ddfb7210a04c5ee7d56fa9a8c209e64414cb74c3f0c17687f2f864bb8", "generation_seconds_batch": 21.029559709015302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5333209037780762, "target_z": 2.3124999931114454, "ce": 5.935244083404541, "genuineness": 4.381826400756836, "identity": 0.5504989624023438, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cc636aa151bf873906d3933099af990ff85e0acb1206968ee2a29cdf69e4c7af.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "cce1fa1f5fd3c805f1a57c09ad7d27e06984757bde8dd112575a61e0d944adb6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0b1f273259694c08930e5a8cbb5c7e8ccab537560ac954186094570d98042320", "generation_seconds_batch": 22.11656731099356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8853063583374023, "target_z": 4.812499938003009, "ce": 5.39911413192749, "genuineness": 4.369274139404297, "identity": 0.3666650056838989, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cce1fa1f5fd3c805f1a57c09ad7d27e06984757bde8dd112575a61e0d944adb6.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "cce697e80158ec6f4392f9eace4d8ae97601a1aecdc49a61731fc6f85632ca1f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59350233f0b7989469c5344abca2db7b4dec1eebe97c82596e07eb2691892be1", "generation_seconds_batch": 16.415260565001518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4910714626312256, "target_z": 2.2343751877131113, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.4998418688774109, "hypothesis": "Road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cce697e80158ec6f4392f9eace4d8ae97601a1aecdc49a61731fc6f85632ca1f.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "ccf99f9ed7ff229650e64bb2795692fb1b0740ce98bba35fdae9c2bf32b367b6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5b1ab332cc305b01915cc62af18ebf41184f10b921b5f03c8afa7ddb8608f285", "generation_seconds_batch": 21.935666568926536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.037404775619507, "target_z": 5.093750030998495, "ce": 5.331601142883301, "genuineness": 4.557555198669434, "identity": 0.5924388766288757, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ccf99f9ed7ff229650e64bb2795692fb1b0740ce98bba35fdae9c2bf32b367b6.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "cd53c3b220e7e2b58bdd40fa84e26bad461b76331dfa377fe464fd5a499e4e64", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fa4de1c847e7761c77357883fcf503e8860dbdcc1d21ef50b84655732f6f103", "generation_seconds_batch": 21.669251760002226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16918867826461792, "target_z": -0.20996093803816832, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.3457798957824707, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cd53c3b220e7e2b58bdd40fa84e26bad461b76331dfa377fe464fd5a499e4e64.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "cdbbf61700ffb061f346327cc1f449fec1c3f8392a838f0cdd02368a1641fd34", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e88b5a55cc12edb2735b2574abbebb46aea3fa2569e713910653d4721ff3e2e4", "generation_seconds_batch": 18.61721174302511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.138803720474243, "target_z": 5.281250092995486, "ce": 5.879645347595215, "genuineness": 4.607763767242432, "identity": 0.7256039381027222, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cdbbf61700ffb061f346327cc1f449fec1c3f8392a838f0cdd02368a1641fd34.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "cde2d2e69be06a0abe969e51f2551aac453e5dde74501d5acd05f2680dd197a8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9653b57634cf87a2442d683f7d9d436fd14dc47059394847aafbed48678d91a6", "generation_seconds_batch": 24.1766748779919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0656652450561523, "target_z": 3.296875098161902, "ce": 5.506340026855469, "genuineness": 4.7834930419921875, "identity": 0.7694807052612305, "hypothesis": "j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cde2d2e69be06a0abe969e51f2551aac453e5dde74501d5acd05f2680dd197a8.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "cdf2cc019a34fc3648f4b5e3e03184ac68a42b1bc24c9f4d745bd1c53bb3889e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9716aeb0a727b3bc52aec046012ac48a34123d87a61e6ed07637255b779d4e12", "generation_seconds_batch": 17.36983169405721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5333209037780762, "target_z": 2.3124999931114454, "ce": 5.502368927001953, "genuineness": 4.319066047668457, "identity": 0.455366313457489, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cdf2cc019a34fc3648f4b5e3e03184ac68a42b1bc24c9f4d745bd1c53bb3889e.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "cea635e3af6618cfee682564e87e5ec28bc7784b7161f307a539023a83497397", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5075d9153313c3e49157968d8f1b95c9297030fa3c674466e6c77fdb65649c17", "generation_seconds_batch": 15.482449827017263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2740023136138916, "target_z": 5.5312501756581405, "ce": 5.311744689941406, "genuineness": 4.582659721374512, "identity": 0.35591626167297363, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cea635e3af6618cfee682564e87e5ec28bc7784b7161f307a539023a83497397.mp3" }, { "id": "heldout-nl-3", "language": "nl", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-3", "key": "cf0573746883459d299959bdffae3ce6bd55650c0cc82167efa2eb707d570596", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "134f5b88e729680636ade4d63fdd39e9ed688784055500d7b13a0c6a8b174f7f", "generation_seconds_batch": 21.224961521918885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9022061824798584, "target_z": 4.843749948335841, "ce": 6.0305562019348145, "genuineness": 4.331617832183838, "identity": 0.46713584661483765, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cf0573746883459d299959bdffae3ce6bd55650c0cc82167efa2eb707d570596.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "edd9f3e1422c700b3fa64c12d97daa9b8c9c94218e060ab6706fc925789501c1", "generation_seconds_batch": 15.295423352974467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3392431139945984, "target_z": 0.10449220827329729, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.6893531084060669, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "cf9a3919943276cc41d66bf7a73b5e53b2d39a10fb5e58b3f36935fce77ee575", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f86242250d1cf0281a0750823584150f23f4e8de474d6bc9faca8451f37bb301", "generation_seconds_batch": 22.427797049982473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071204423904419, "target_z": 5.156250051664159, "ce": 4.810363292694092, "genuineness": 4.319066047668457, "identity": 0.5402193069458008, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cf9a3919943276cc41d66bf7a73b5e53b2d39a10fb5e58b3f36935fce77ee575.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "cfc57038c6a5edbd7a57fbe17942a483297d81a3319806aa64e790aea83c2abc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c395cbe9ae2b647449f53f0f25195f4e48fd4787789912d6060ad8a7d6b49bf", "generation_seconds_batch": 20.815682041924447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.020504951477051, "target_z": 5.062500020665664, "ce": 5.458683967590332, "genuineness": 4.557555198669434, "identity": 0.28140097856521606, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/cfc57038c6a5edbd7a57fbe17942a483297d81a3319806aa64e790aea83c2abc.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "d060bd93d5ea7f0217288112a4c5a70276ff1bbccd2fea6ad78b83adad1755c6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c455f381b5e3d475c255595102c8500571d38b503b8f15c1f43c244820659e50", "generation_seconds_batch": 21.207572338054888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18872909247875214, "target_z": -0.17382812736794062, "ce": 6.205295085906982, "genuineness": 4.7081804275512695, "identity": 0.4829704165458679, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d060bd93d5ea7f0217288112a4c5a70276ff1bbccd2fea6ad78b83adad1755c6.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "d0b5bbd04be9db9429228f92af321e71908f1ef4f06ae68b84451d3c0e60a29f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25096e711353cb2f47ab969f03ea3713e545503f1ba67f2cd28c9bdacf68e7bc", "generation_seconds_batch": 17.424021094106138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6516196727752686, "target_z": 2.531250065441268, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.6334693431854248, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d0b5bbd04be9db9429228f92af321e71908f1ef4f06ae68b84451d3c0e60a29f.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "d0c6fca8c8a206d5bced041406713fa525e405eef7ebe272f7c5bd449d261a5b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a63e924b26fe94d86cee232a7ba4792ac71577592fecaaced80a098a468a462", "generation_seconds_batch": 22.202552821021527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.465721607208252, "target_z": 2.187499951780118, "ce": 6.022613525390625, "genuineness": 4.319066047668457, "identity": 0.5567964911460876, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d0c6fca8c8a206d5bced041406713fa525e405eef7ebe272f7c5bd449d261a5b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "d0cb6005153ddaf153b4d7c5afccf1d087319a6579ea1cbf1ccc0f7dc234e76a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9375bf876a561805e52ee6ebe5494fb65409bdd33b57225f738a3a0e481d0e37", "generation_seconds_batch": 20.69661540305242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.836203396320343, "target_z": 1.0234375077496238, "ce": 6.062326908111572, "genuineness": 4.582659721374512, "identity": 0.6975990533828735, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d0cb6005153ddaf153b4d7c5afccf1d087319a6579ea1cbf1ccc0f7dc234e76a.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36108531f3a3fe94162578accd2eb3b28bc69245797a49590686e5a50d23be64", "generation_seconds_batch": 17.000126819009893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07465532422065735, "target_z": -0.3847656144519009, "ce": 6.41180419921875, "genuineness": 4.218649387359619, "identity": 0.3475914001464844, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "d11d303205c6d0826abc2c4b8328ef3d2f09ec8abbc2372270594c8cfeb58e9c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ca4ede3d4d1c7fa70f5a9bed372a09b072ec1e9265fed7adf3a754cadbddeda", "generation_seconds_batch": 20.52542274899315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2911842465400696, "target_z": 0.015625005166415906, "ce": 6.149696350097656, "genuineness": 4.15588903427124, "identity": 0.3847877085208893, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d11d303205c6d0826abc2c4b8328ef3d2f09ec8abbc2372270594c8cfeb58e9c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "d18ed35cdbbbe6ee7b339e39df10d9c070106790e5b616c536cfc6c34eea3a60", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5eff41bed5ca9373c49807e66dd7c7a38b3ae2930e20f5cb3a8b937c3ccfdcb", "generation_seconds_batch": 21.581662795040756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5164210796356201, "target_z": 2.2812499827786135, "ce": 6.125868320465088, "genuineness": 4.7332844734191895, "identity": 0.4863419532775879, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d18ed35cdbbbe6ee7b339e39df10d9c070106790e5b616c536cfc6c34eea3a60.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "d191044502524a917e774ca61c269e360c80b94cb013cb59097ea6564ba442b0", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47d90e16502d11b26260265caff01bf84cdd47af10c128c79e08264c4e5c3385", "generation_seconds_batch": 21.684136152034625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3614120483398438, "target_z": 3.843750058552714, "ce": 5.295859336853027, "genuineness": 4.356721878051758, "identity": 0.6264116764068604, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten, gemeinsam hineinschauend.", "wer": 0.25, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d191044502524a917e774ca61c269e360c80b94cb013cb59097ea6564ba442b0.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "d19590e69efe21b1800bddcf121817d405f8ccc03c22c570c8b032b8c4d71884", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9654915492a2c583206e3a0d0396749c75c8bc1542fe9a7b3f0d1e0415a053c8", "generation_seconds_batch": 20.698475447949022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2233028411865234, "target_z": 5.437500144659645, "ce": 5.855817794799805, "genuineness": 4.469690799713135, "identity": 0.47722992300987244, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d19590e69efe21b1800bddcf121817d405f8ccc03c22c570c8b032b8c4d71884.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "d1d97321f6ecff5bc2c1c9d76c8dc0f4c2fa700aa617cbbf3dd326a0d17938b0", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bad0e6e1d4dc1e7e7ebcc0df9e6b6903fde18f8daaa1b5365fcf8fce27268800", "generation_seconds_batch": 16.184819745016284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.803718090057373, "target_z": 2.8125001584367544, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.21144600212574005, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d1d97321f6ecff5bc2c1c9d76c8dc0f4c2fa700aa617cbbf3dd326a0d17938b0.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "d1e53d1b187e0f7892f84a08fb4f3f35ad7a952a983f409f494ba1daf1959b75", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee8f619aaaa135cf8c64b8bb855171d1bbc0ac74365270d12be4bcad0e0264ca", "generation_seconds_batch": 20.339053595089354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9840767979621887, "target_z": 1.2968749879450296, "ce": 5.9431867599487305, "genuineness": 4.68307638168335, "identity": 0.8018553256988525, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d1e53d1b187e0f7892f84a08fb4f3f35ad7a952a983f409f494ba1daf1959b75.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "d2116ea7956b4163816af1ccd25cc4803215e52f0e98d0c1563f4e52281c7461", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce64b203450563da4e68b549a9133f910361569265457c176715e6ad8c8f3f0a", "generation_seconds_batch": 15.614563695038669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8911278247833252, "target_z": 1.1250000413313272, "ce": 6.157639026641846, "genuineness": 4.946669578552246, "identity": 0.7946758270263672, "hypothesis": "J'ai trouvé petite boîte. Elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d2116ea7956b4163816af1ccd25cc4803215e52f0e98d0c1563f4e52281c7461.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aeb1c7f9ced9d4c83d2f325654ef0357d6d6a66cfd54b5f62f0423d5b6106c9f", "generation_seconds_batch": 15.856443743105046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3619522452354431, "target_z": 0.14648439588093096, "ce": 6.213237762451172, "genuineness": 4.18099308013916, "identity": 0.7011587619781494, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "d2624c12aeeeaf2c82f0beb01bb1ed4fc2d0bfef042dfdd9b4413b9d9cfaebc5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89a7c9cae1b4be4ddf3139ddf33d2f492eea1af6306dd6cbc4740599b855f159", "generation_seconds_batch": 20.885591575992294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.375401258468628, "target_z": 5.718750237655132, "ce": 5.311744689941406, "genuineness": 4.325342178344727, "identity": 0.15938800573349, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d2624c12aeeeaf2c82f0beb01bb1ed4fc2d0bfef042dfdd9b4413b9d9cfaebc5.mp3" }, { "id": "heldout-en-1", "language": "en", "sentences": [ "The keys are on the kitchen table.", "I checked the drawer... then looked beside the window.", "Take them with you when you leave." ], "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-1", "key": "d2646fbed98d753f04c3fc1266354a2a80110276d6b69fb583678681056bd7b9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2fc745d2ff9d6c60f42e6c595fa8b7e2d5c0dca6424ed9395f15f5efb52f845", "generation_seconds_batch": 15.058596579008736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1826496124267578, "target_z": 1.664062388922058, "ce": 5.863759994506836, "genuineness": 4.482243061065674, "identity": 0.4506978988647461, "hypothesis": "Yikis are on the kitchen table. I check the drawer. Then looked beside the window. Take them with you when you leave.", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d2646fbed98d753f04c3fc1266354a2a80110276d6b69fb583678681056bd7b9.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "d275e9d1835b47a383811dfb89363a506b63cd05d917ac7c2d602797fab53e30", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9faa131fe739b461a7b2bf4d4f3ed0940451a24ac1242334e8f716cb9113ae8", "generation_seconds_batch": 21.466921393061057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2079994678497314, "target_z": 1.710937624855051, "ce": 5.863759994506836, "genuineness": 4.758388519287109, "identity": 0.6315898299217224, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d275e9d1835b47a383811dfb89363a506b63cd05d917ac7c2d602797fab53e30.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "d2b92698c7d868a32a04854577fe977bb45246d46f4565cdbea9c3cd8af36422", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff0ca49892453e40b0fb182bab37e42c9d09db840d8a308d6ffff75c5b5dc92d", "generation_seconds_batch": 21.822854639030993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2977857291698456, "target_z": 0.02783201978701471, "ce": 5.744620323181152, "genuineness": 4.068024158477783, "identity": 0.44528260827064514, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d2b92698c7d868a32a04854577fe977bb45246d46f4565cdbea9c3cd8af36422.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "d2d7694c99f552ced17533b0de15bcbb70c40199a6423db178a167eb5a93388d", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55d8fa3a48172a07032d689be5f9698c94480f08edf10284ebef1c6d00c679ff", "generation_seconds_batch": 14.844384640920907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04930558800697327, "target_z": -0.4316406299511486, "ce": 6.300607204437256, "genuineness": 4.293961524963379, "identity": 0.4432707130908966, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d2d7694c99f552ced17533b0de15bcbb70c40199a6423db178a167eb5a93388d.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "d30beea8f086046fbaaf8e9ef04be6a207ae9d2eaf11cc94e96b5c4338d87f3b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "524ae8ac1821a47ec35c2150a20f7fc5e0dd39bc416d8cd24cb34b2d75966760", "generation_seconds_batch": 16.028621101984754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7276687622070312, "target_z": 2.671874891505266, "ce": 5.061550617218018, "genuineness": 4.3127899169921875, "identity": 0.5534026622772217, "hypothesis": "Escribí el número en el sobre Lowe y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d30beea8f086046fbaaf8e9ef04be6a207ae9d2eaf11cc94e96b5c4338d87f3b.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "d3f4ae6474d9d64d850f2150f1c6acae4f53937ddf9563a69e7e772873f3c494", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8288f103e000c6ef8a3c7ade07cb416ef4a4011ce5fa2eb6a0c3b1975e6229e", "generation_seconds_batch": 20.581072889035568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.733208179473877, "target_z": 4.531250285875013, "ce": 5.601652145385742, "genuineness": 4.570107460021973, "identity": 0.683558464050293, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d3f4ae6474d9d64d850f2150f1c6acae4f53937ddf9563a69e7e772873f3c494.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f66cad82e316c866a59670e3590eb33428aada54eec8ff4aa5a7ace22131a53a", "generation_seconds_batch": 18.673215952003375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00599980354309082, "target_z": -0.5117187538748119, "ce": 5.959072113037109, "genuineness": 4.331617832183838, "identity": 0.7572189569473267, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "d43f68ee3e3f14fb0113d2304e798b9018e2106d1ed253d3620b6431cd9b57a2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56cd8fa142ba3814e19b478ada018558831e768c5f5f11613201f135dfc50dad", "generation_seconds_batch": 22.021634074044414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3262982368469238, "target_z": 1.9296876971848738, "ce": 5.375286102294922, "genuineness": 4.482243061065674, "identity": 0.5630289316177368, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d43f68ee3e3f14fb0113d2304e798b9018e2106d1ed253d3620b6431cd9b57a2.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "d44edfa78201219a3ffaf6ebd3bc1d65f17c4f1587e31bba2b73d73cba08be09", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2298818e7c4f8b2f395b72298e759294067c5eb458c3e77fcee178928975522", "generation_seconds_batch": 20.25352051097434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.823528528213501, "target_z": 1.0, "ce": 6.324435234069824, "genuineness": 4.6203155517578125, "identity": 0.5312975645065308, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d44edfa78201219a3ffaf6ebd3bc1d65f17c4f1587e31bba2b73d73cba08be09.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "d4afb3ee54bacc2124a166155c9b744d492af1bc01a773e46aed86067d03f6ae", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "375e2a0e01f94f4b3cb1284d61068d76a4d1a3feda5ad0142d1ac84310791737", "generation_seconds_batch": 21.822854639030993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2460240125656128, "target_z": 1.78125003788705, "ce": 5.863759994506836, "genuineness": 4.3127899169921875, "identity": 0.4406578540802002, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d4afb3ee54bacc2124a166155c9b744d492af1bc01a773e46aed86067d03f6ae.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "d4c1c869f1fef24d0a80bfd1d839c750218442050acff6bbabfd395c9ab58162", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50be2a53b534c59b0fa6c9e188ee9561e20b220d781f386c0ccc740bc31ff566", "generation_seconds_batch": 20.991344004985876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.839932441711426, "genuineness": 4.607763767242432, "identity": 0.705500602722168, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d4c1c869f1fef24d0a80bfd1d839c750218442050acff6bbabfd395c9ab58162.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "d6a51d1dec9c911246537ac6cd787b05d68ef0929e6b3e4b24f386dfccd6745d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64fe73d74ab2067d6fb849becbd9e72572a83e3c5ee3c8fa8267b1d816c28ea1", "generation_seconds_batch": 21.669251760002226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6503053903579712, "target_z": 0.6796875043053466, "ce": 6.483288764953613, "genuineness": 4.770940780639648, "identity": 0.4155677556991577, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d6a51d1dec9c911246537ac6cd787b05d68ef0929e6b3e4b24f386dfccd6745d.mp3" }, { "id": "heldout-nl-0", "language": "nl", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-0", "key": "d6ca2c5c88d8f2b528f2971ede6b8fce28c9f382156b6c176433b2dd54f1fa10", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "adcdaf715073536f4c9c0e99e6a11cb8071fb71b125d8df71301308ea20ef235", "generation_seconds_batch": 20.95358872995712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9529056549072266, "target_z": 4.937499979334336, "ce": 5.689021587371826, "genuineness": 4.65797233581543, "identity": 0.4148704409599304, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zou maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d6ca2c5c88d8f2b528f2971ede6b8fce28c9f382156b6c176433b2dd54f1fa10.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "d7a196b1e81f95d751957eb9525b0f5f1c19a0807864ae107aae030b754c00a9", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15a6b6a72202237f8430e7c518800be6a2d1d06842c5bb1f9d7fcb76bdbda02a", "generation_seconds_batch": 22.589740323019214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.412111520767212, "target_z": 3.937500089551209, "ce": 5.824047088623047, "genuineness": 4.6203155517578125, "identity": 0.7744308710098267, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d7a196b1e81f95d751957eb9525b0f5f1c19a0807864ae107aae030b754c00a9.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "d8a574103c8430baf741f99c58e24d74a563261a2237b60a26eb95bb25efd782", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51cb604a8ca4b66643fbc753ce94428bb1140f86b6b22093cefc54fb5de4a4a6", "generation_seconds_batch": 21.219401914044283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6460804343223572, "target_z": 0.6718750017221387, "ce": 5.95112943649292, "genuineness": 4.720732688903809, "identity": 0.7858721613883972, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d8a574103c8430baf741f99c58e24d74a563261a2237b60a26eb95bb25efd782.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "d8c61a8a463709868d7dafa80c927a861a7b8f5c7cd13b07839f1cf5d2fb5fa2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ddc6ec88b1e315039c1a7ea63f028e922b4d4da130d6240c89c249faf920580d", "generation_seconds_batch": 23.34330838394817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2909021377563477, "target_z": 5.562500185990973, "ce": 5.40705680847168, "genuineness": 4.68307638168335, "identity": 0.6734062433242798, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d8c61a8a463709868d7dafa80c927a861a7b8f5c7cd13b07839f1cf5d2fb5fa2.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "d8d37329ff1fd3a0006f19eb462f0ceafb2981fd64dae247e66640c0f404d091", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0392fd9d0a8f975c17e2faabe599cf80b6806abc1d37565858ed50464f11e941", "generation_seconds_batch": 19.71491714695003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.105004072189331, "target_z": 5.218750072329823, "ce": 5.522225379943848, "genuineness": 4.532451152801514, "identity": 0.5834429264068604, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d8d37329ff1fd3a0006f19eb462f0ceafb2981fd64dae247e66640c0f404d091.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "d960406fa61d54af3a0f9bf67d9c113d997d1a1b65780d05f0503685de5584d2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a31025f7b335119fe2c6549518bc428436d22298f1c9717676e24e3ec7b79580", "generation_seconds_batch": 21.664111986989155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21038198471069336, "target_z": -0.13378906540610894, "ce": 6.340320587158203, "genuineness": 4.632867813110352, "identity": 0.46946558356285095, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d960406fa61d54af3a0f9bf67d9c113d997d1a1b65780d05f0503685de5584d2.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "d9b3ce3a2b7bc28c567e9f493e5d8ce236cab53cf7a576b3d9b77520cbdc4c38", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7750f85b09c1ee3121ffd8d3d2554c335f5d5a548be52e4416a6ef56cbb49d1b", "generation_seconds_batch": 16.290968342102133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4036617279052734, "target_z": 3.9218753048185384, "ce": 5.101263999938965, "genuineness": 4.68307638168335, "identity": 0.7527735233306885, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d9b3ce3a2b7bc28c567e9f493e5d8ce236cab53cf7a576b3d9b77520cbdc4c38.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "d9d4046ea0592a7fde00c4ee7189d277856bc1f72db621ac53b98ef390601380", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4c895318b94d369e7d8e35893448879eaa51df639e17ade91d2f11493edc41e", "generation_seconds_batch": 26.590537630021572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2241130918264389, "target_z": -0.1083984320106831, "ce": 6.308549880981445, "genuineness": 4.557555198669434, "identity": 0.42662596702575684, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d9d4046ea0592a7fde00c4ee7189d277856bc1f72db621ac53b98ef390601380.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "d9fa61c53d4629ce58508972ab55556323a5a08761a3b9c07256da9775066afd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b16049be8d5d96bd499c6e5a2ad5eb5e601df8b052718ca0f6867cdf179544e9", "generation_seconds_batch": 16.264868042082526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6685194969177246, "target_z": 2.5625000757741, "ce": 5.9431867599487305, "genuineness": 4.394378662109375, "identity": 0.3027398884296417, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/d9fa61c53d4629ce58508972ab55556323a5a08761a3b9c07256da9775066afd.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "da7d9922697d86d08e95d5183f8c507f71216587e7b78da3e9c5efd558b08d5e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d8c7fcbb834b082f1e5666da8a27de762de1fec563701b663dfbb1c2f420a7b", "generation_seconds_batch": 21.40406523901038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2291241884231567, "target_z": 1.7500000275542182, "ce": 6.149696350097656, "genuineness": 4.432034492492676, "identity": 0.48086583614349365, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/da7d9922697d86d08e95d5183f8c507f71216587e7b78da3e9c5efd558b08d5e.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "dadf735065201f20abf9d76be771039c7c670d1582c02d1c4d34a2ba334beb5f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6573923efd22873f001433aa2d21660afb698805d305a2d175d73cede5051445", "generation_seconds_batch": 22.831985929980874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.037404775619507, "target_z": 5.093750030998495, "ce": 4.936453342437744, "genuineness": 4.331617832183838, "identity": 0.843082070350647, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dadf735065201f20abf9d76be771039c7c670d1582c02d1c4d34a2ba334beb5f.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "dae8ff9a2dcfa5f7f1c8648452c8037af9880b1b75d375cfe7c92da94c221f0c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "efe4910c5f2f57d18019de4c8845aac6b8c45eb00d137f5b057c042f531de8b2", "generation_seconds_batch": 15.378730869968422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1023755073547363, "target_z": 1.5156249500579795, "ce": 5.839932441711426, "genuineness": 4.7458367347717285, "identity": 0.8444556593894958, "hypothesis": "Les clés sont sur la table de la cuisine, j'ai regardé dans le tiroir, puis près de la fenêtre, prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dae8ff9a2dcfa5f7f1c8648452c8037af9880b1b75d375cfe7c92da94c221f0c.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "db1149cb19a1fc452e3dacbb6d0e5020ec400ce2f35e040ae9836d0ccde7758f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb49c0bb96ec00e1e5f6868c15877434e7b0c7751c7358b5ed1b8c4320f3e113", "generation_seconds_batch": 22.510171758942306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9671769738197327, "target_z": 1.2656249776121977, "ce": 6.213237762451172, "genuineness": 4.770940780639648, "identity": 0.5493006706237793, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/db1149cb19a1fc452e3dacbb6d0e5020ec400ce2f35e040ae9836d0ccde7758f.mp3" }, { "id": "heldout-en-0", "language": "en", "sentences": [ "Your message arrived after I had left.", "I read it twice... before putting the phone away.", "Let me know when we can talk." ], "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-0", "key": "db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdb8fbff419746126918bb0d25bfc09beb3940cb4d6970343968bf6c7ec48db8", "generation_seconds_batch": 15.201117038959637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6228431463241577, "target_z": 0.6289061824060586, "ce": 6.467403411865234, "genuineness": 4.444586753845215, "identity": 0.36070987582206726, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "heldout-nl-4", "language": "nl", "sentences": [ "Ik schreef het nummer op de envelop.", "Lees het goed... en controleer de laatste twee cijfers.", "Bel me wanneer je even tijd hebt." ], "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-4", "key": "db958034344b884ab01a9af490286963a171a7f7681fda550508f447237d77f7", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "814a0083d27079aade614559d9aa4e03a1378cf39977b134529c5491ce48f9dc", "generation_seconds_batch": 16.752011255943216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2402026653289795, "target_z": 5.4687501549924775, "ce": 5.998785495758057, "genuineness": 4.268857479095459, "identity": 0.20941045880317688, "hypothesis": "Ik schreef het nummer op de envelop. Lues het goed. En controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/db958034344b884ab01a9af490286963a171a7f7681fda550508f447237d77f7.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "dc49e5382059c307cf9d46ff37d5f80c141a2aaf3bc9c8ab90752f85b0137886", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3b5298ad0b0508e228123aa45bce671da5a67ba8336e4552229668ea82c63f5", "generation_seconds_batch": 16.81504918599967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750108003616333, "target_z": 4.562500296207845, "ce": 5.534139156341553, "genuineness": 4.507347106933594, "identity": 0.7197661995887756, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dc49e5382059c307cf9d46ff37d5f80c141a2aaf3bc9c8ab90752f85b0137886.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "dc9bfccbede40124f824e3281f1eb8f1755e1273f6460ccbbbc3dc2205b48bdc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "162bd9930a278a75f2c267e2ce3bea8daca435875c787f13797f9cfe15e5759a", "generation_seconds_batch": 21.08501213300042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7432544231414795, "target_z": 0.8515625611359215, "ce": 6.1894097328186035, "genuineness": 4.883909225463867, "identity": 0.765221357345581, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dc9bfccbede40124f824e3281f1eb8f1755e1273f6460ccbbbc3dc2205b48bdc.mp3" }, { "id": "heldout-fr-4", "language": "fr", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-4", "key": "dd45d87abca6c163c32cd2ab943e3c24446709a0165362fa367328e503e0fee2", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e16d1411cf7d4d2dd1483c00179f445e20dc1eb98117dfb4ab51187818d01b6", "generation_seconds_batch": 16.124050904996693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3783118724823, "target_z": 3.8750000688855453, "ce": 5.434855937957764, "genuineness": 4.532451152801514, "identity": 0.7872229814529419, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dd45d87abca6c163c32cd2ab943e3c24446709a0165362fa367328e503e0fee2.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "de67bb35be82a58c827356077d8a1f4ab6eb1faf3f4c3b7839d84047ea8d3fa9", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9917f70dc81cf369950c6c8b537e68469b1ff42fd50792dc614e4d5ce598e594", "generation_seconds_batch": 21.36921309493482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1868746280670166, "target_z": 1.6718750017221387, "ce": 6.109982967376709, "genuineness": 4.871357440948486, "identity": 0.6046901941299438, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/de67bb35be82a58c827356077d8a1f4ab6eb1faf3f4c3b7839d84047ea8d3fa9.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "dec70eba94e69dec1c64e5fdaa10294726c240e1659e936dc67a764ff17fd668", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56cdba652ab9fbd69f70774776d00e782fd878d48997dc2abbff5ff036848cad", "generation_seconds_batch": 16.0709753370611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8797671794891357, "target_z": 2.9531249845007523, "ce": 5.478540420532227, "genuineness": 4.557555198669434, "identity": 0.5665276050567627, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dec70eba94e69dec1c64e5fdaa10294726c240e1659e936dc67a764ff17fd668.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "dee0cb3cd8f705d062a4cae02382c832904fdbd44e621137261fe5ec2b06f630", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95f2f28ffc4150f027ef3f2c8241ab00e615f6c4199ea213a50029c44cb407d8", "generation_seconds_batch": 23.34330838394817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9529056549072266, "target_z": 4.937499979334336, "ce": 5.486483573913574, "genuineness": 4.720732688903809, "identity": 0.5983271598815918, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dee0cb3cd8f705d062a4cae02382c832904fdbd44e621137261fe5ec2b06f630.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "dee244130f46485133cc96e0e54176729c47764b1f1a3efc88a4077830c5568d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd69afc6f2f3173f41dfb65ca84969ef393fba8c10eac7c50bf35059edc46bc3", "generation_seconds_batch": 19.768059963011183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4374613761901855, "target_z": 3.984375325484202, "ce": 5.426913261413574, "genuineness": 4.494794845581055, "identity": 0.6606309413909912, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dee244130f46485133cc96e0e54176729c47764b1f1a3efc88a4077830c5568d.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "df192322cf736b8e214baa061facec511fdded90d2dfa48523afb313d9a74ea3", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a71455cc39117f68f05bdc26d33c8c26ce5d9c553b87b7eb268f984c9beaafb2", "generation_seconds_batch": 22.552604004042223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36512094736099243, "target_z": 0.15234374526411876, "ce": 6.252951145172119, "genuineness": 4.143336772918701, "identity": 0.1754515916109085, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/df192322cf736b8e214baa061facec511fdded90d2dfa48523afb313d9a74ea3.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "df72bf55927eeb47af2b4aeb03a1bd7dd4c873cf270bf8f0e6c8d3e64a8f04ce", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "14c2ac2a85068c0b0af2067992d6cbd646f2261c5e5f08f6f626f5e5e4060e5a", "generation_seconds_batch": 17.915229376987554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.750108003616333, "target_z": 4.562500296207845, "ce": 5.71682071685791, "genuineness": 4.231201171875, "identity": 0.7334054708480835, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/df72bf55927eeb47af2b4aeb03a1bd7dd4c873cf270bf8f0e6c8d3e64a8f04ce.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "dfb53aad2d639c9cf232d045161fa143ce21bc2330cec25b0423ee02483681ca", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5770374b23bde25dae78e07b147466e550a571c88df993903909b3cc4f2e38a5", "generation_seconds_batch": 22.238883596961387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1749979853630066, "target_z": -0.19921876076336648, "ce": 6.205295085906982, "genuineness": 4.413206577301025, "identity": 0.4169515073299408, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dfb53aad2d639c9cf232d045161fa143ce21bc2330cec25b0423ee02483681ca.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "dfd625cf9922e9e84acce0328a50b702e78f89e05abfea118263dabab21d7363", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0daf2a77e602ca89b91b922918022dc7f39d53ee766c522235c63736a1b3c73c", "generation_seconds_batch": 15.816768061951734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.073464393615723, "genuineness": 4.507347106933594, "identity": 0.6709426641464233, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/dfd625cf9922e9e84acce0328a50b702e78f89e05abfea118263dabab21d7363.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "e088de1dcb63dd9cd60daaa8daec311831fc49748333718c701cb65d713729e8", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84eb3cb596dcd3129db697b7786dcc7691dec15798098905aeeb825ab9d35bb1", "generation_seconds_batch": 17.527641886030324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302262783050537, "target_z": 3.7343752428215473, "ce": 5.808161735534668, "genuineness": 4.532451152801514, "identity": 0.32590240240097046, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e088de1dcb63dd9cd60daaa8daec311831fc49748333718c701cb65d713729e8.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "e0a342daa3f9eeeb883ffffb1191df3b9c4add45db8a204a109339922edbf116", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24a7a0c9f09660aacfa5f15f3a5c5f951be325cedf310d4648df6bd6099e136e", "generation_seconds_batch": 14.301881296094507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.676969289779663, "target_z": 2.5781248605067706, "ce": 6.054384231567383, "genuineness": 4.319066047668457, "identity": 0.5477352142333984, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e0a342daa3f9eeeb883ffffb1191df3b9c4add45db8a204a109339922edbf116.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "e1c4dc873566ab25471ffc00dc3ed15c709a9407c8490dfc0c5b9a06af00c6a6", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83bb597f31d67f742abffbaaa41ead1b87184562aa272d8425b623ecc02abb17", "generation_seconds_batch": 22.6065194880357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.676969289779663, "target_z": 2.5781248605067706, "ce": 5.772419452667236, "genuineness": 4.645420074462891, "identity": 0.7397329807281494, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e1c4dc873566ab25471ffc00dc3ed15c709a9407c8490dfc0c5b9a06af00c6a6.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "e1c5154dbbedcd2294a5ab844eaa103474a09df3392937f3b78ed8ec0ef3fcc8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "effeca030fae0e4401ee3be777225ced38cd02195e7ef3b316fc4bb160defcfc", "generation_seconds_batch": 17.187170448014513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5781989097595215, "target_z": 6.093749920781622, "ce": 5.780362129211426, "genuineness": 4.7081804275512695, "identity": 0.7069398760795593, "hypothesis": "Cuando alguien ha movido, la pequeña silla azul estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e1c5154dbbedcd2294a5ab844eaa103474a09df3392937f3b78ed8ec0ef3fcc8.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "e20ff1e5cfc16481ef5cf79b73a280dcdaf7ec82f7a67ef382e7f8f439298700", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f182682d3733165436b3c42b7ab91949d37b749fd84f054631c47322bcf0c627", "generation_seconds_batch": 21.639599507907405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6854193210601807, "target_z": 2.593750086106932, "ce": 5.919358730316162, "genuineness": 4.3504462242126465, "identity": 0.6145216226577759, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e20ff1e5cfc16481ef5cf79b73a280dcdaf7ec82f7a67ef382e7f8f439298700.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "e22a37598ea7ebce03218b05fdffaa616bbafc73319168fa171860eef4cab143", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a96fefd8195a13bbfe37ee1babea7f2befb11cb43a70ec11a73fa9a08b8fbd67", "generation_seconds_batch": 25.20542045496404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5248711109161377, "target_z": 2.2968752083787747, "ce": 6.046441555023193, "genuineness": 4.444586753845215, "identity": 0.6600266695022583, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e22a37598ea7ebce03218b05fdffaa616bbafc73319168fa171860eef4cab143.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "e241c10a7468ce2aa820700b3ef5ffb9404437ed51f01b0e8923043a44e3ea2d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ad819eb0abff366625c0b9a70d813e522cf01bf81971846c41593e144b7a5bca", "generation_seconds_batch": 21.61583005997818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9051170349121094, "target_z": 3.0000002204337455, "ce": 5.736677646636963, "genuineness": 4.469690799713135, "identity": 0.19627489149570465, "hypothesis": "The door still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e241c10a7468ce2aa820700b3ef5ffb9404437ed51f01b0e8923043a44e3ea2d.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "e3077a8ecaccfeee0fc94060d48c875b6671b97024fb6b2bcf672777f5a30c73", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8843f5c45a2e367e9a61cba110408a43bf5607149f9ebcad88252f9a05ff893", "generation_seconds_batch": 19.484985443064943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0939257144927979, "target_z": 1.500000165325309, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.5879095792770386, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e3077a8ecaccfeee0fc94060d48c875b6671b97024fb6b2bcf672777f5a30c73.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "e31e4f03583cec03350ac05fb2f6a4f978603dd7d4ad6dcb734bda1ebe1bc529", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb11400ea3feb059a1e0e215302bcfc2b2a0702881c2bf300840088e4e94320c", "generation_seconds_batch": 20.861773938057013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.803718090057373, "target_z": 2.8125001584367544, "ce": 5.71682071685791, "genuineness": 4.381826400756836, "identity": 0.6202472448348999, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e31e4f03583cec03350ac05fb2f6a4f978603dd7d4ad6dcb734bda1ebe1bc529.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "e38f2fa6e72890600f07e7d6e9e6a1e3d4575d0ba98b974aecf898fe276b846f", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be2e3b13ef54479b405ff15bff01da2190f0c45a4185c89ef792807be6273c61", "generation_seconds_batch": 22.427797049982473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9022061824798584, "target_z": 4.843749948335841, "ce": 4.818305969238281, "genuineness": 4.557555198669434, "identity": 0.6680845618247986, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e38f2fa6e72890600f07e7d6e9e6a1e3d4575d0ba98b974aecf898fe276b846f.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "e3da4c36dcfb0db03fe9847edc6181bec57f58db6a338562d2aa68a15a0b209a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "629ebe204bbb30e74c3fb895c899cb72f521c6c9ca3269a126763b1118dee847", "generation_seconds_batch": 21.849317504907958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.071204423904419, "target_z": 5.156250051664159, "ce": 5.307773113250732, "genuineness": 4.457139015197754, "identity": 0.46925511956214905, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e3da4c36dcfb0db03fe9847edc6181bec57f58db6a338562d2aa68a15a0b209a.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "e42e02636810664e0c28d7481ef9593d53d73ed3f08e7225c33fa3e3586fb860", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a040e12bee98165166593387740fbbd401c1c1bd3c5911f8aaa647b39be44343", "generation_seconds_batch": 21.617633719928563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48553216457366943, "target_z": 0.37500001377710906, "ce": 6.300607204437256, "genuineness": 4.6705241203308105, "identity": 0.49017369747161865, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e42e02636810664e0c28d7481ef9593d53d73ed3f08e7225c33fa3e3586fb860.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "e4e3adc2151a1e364f60c3198a0bd4b4e186f99c867f4baaf36b7bb2c7e3312c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a0314423831f2a02d7aa66d63ecf6abec97439a7c30aec6703c6dd7f38537af", "generation_seconds_batch": 20.77117625705432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2909021377563477, "target_z": 5.562500185990973, "ce": 5.6532793045043945, "genuineness": 4.413206577301025, "identity": 0.1235726848244667, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e4e3adc2151a1e364f60c3198a0bd4b4e186f99c867f4baaf36b7bb2c7e3312c.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "e505737db199e2436585af96686b35fbdc2e0c21386bec4a33d2a419fc125319", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d023e6a1a88375daab3987ee0650e5d26e54446bf6ce664f039e63faafa1c3bc", "generation_seconds_batch": 21.36921309493482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4572718143463135, "target_z": 2.1718751670474474, "ce": 5.863759994506836, "genuineness": 4.796044826507568, "identity": 0.6863957643508911, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e505737db199e2436585af96686b35fbdc2e0c21386bec4a33d2a419fc125319.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "e5909eab897a12211c905835ae731a1a5b8f424d5b515bca0005bca07b2949f4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "113a31a6040e34d47b46bdf7aa7ec1f241f30fb148c331b3f243183bccc56e93", "generation_seconds_batch": 20.982883992022835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.46281099319458, "target_z": 4.031250120549704, "ce": 4.939431667327881, "genuineness": 4.381826400756836, "identity": 0.4533569812774658, "hypothesis": "Me he encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e5909eab897a12211c905835ae731a1a5b8f424d5b515bca0005bca07b2949f4.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "e5f1f7997ce5d24ad97a6ffd27906fd9f8e9a5f32c0cde4d3d4e8eeb04b7daf7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcc9824af7ed240c93895046cd3205848feef56da2a3e5ab6d6b3cafc3274e1d", "generation_seconds_batch": 21.788898220984265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.375401258468628, "target_z": 5.718750237655132, "ce": 5.230332374572754, "genuineness": 4.406930446624756, "identity": 0.700766384601593, "hypothesis": "La puerta sigue abierta he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e5f1f7997ce5d24ad97a6ffd27906fd9f8e9a5f32c0cde4d3d4e8eeb04b7daf7.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "e66c25996d73824fd59ff2854a6651145d6c351b36e4e54ea1bf822a643f3d10", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25fd97a20bfa8685474783cc8c46ec8f86e65e4a04753584873b1ac9d62ed40b", "generation_seconds_batch": 19.484985443064943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4150221347808838, "target_z": 2.093749920781623, "ce": 6.23706579208374, "genuineness": 4.6705241203308105, "identity": 0.5702096223831177, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e66c25996d73824fd59ff2854a6651145d6c351b36e4e54ea1bf822a643f3d10.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "e69b26bf251b478f9d2c2010555ecba0cd3ada3711209427775864ddcf63d8ab", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64454345a29179c6398f9883d58bd868677a41e162a0c59eecde731347610dfa", "generation_seconds_batch": 16.126924780081026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.175513982772827, "target_z": 3.4999999448915635, "ce": 5.474569320678711, "genuineness": 4.419482707977295, "identity": 0.6342611312866211, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e69b26bf251b478f9d2c2010555ecba0cd3ada3711209427775864ddcf63d8ab.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "e6afc574dad97b1049600602f045169171affef5ab231bff3c264e4f6ae673cc", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8946d9cac72a137f02487b530884f44279698f80f0bd7e0f074be3af87718387", "generation_seconds_batch": 15.150018464075401, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0221014022827148, "target_z": 1.3671875111939011, "ce": 5.80021858215332, "genuineness": 4.65797233581543, "identity": 0.7085939645767212, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e6afc574dad97b1049600602f045169171affef5ab231bff3c264e4f6ae673cc.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90fdd08d3856b3c019136f9282159f29844f0894f430dcab82e8701a4aee10ff", "generation_seconds_batch": 17.20113930304069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15704193711280823, "target_z": -0.2324218691877821, "ce": 6.435632705688477, "genuineness": 4.3504462242126465, "identity": 0.3248571753501892, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "e74e0287e0f53b19df5d2614751cc1ed478f0f3a15934b5bae7bb19e17042076", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00b9452fbef832f7c137357a64d9eec1272a73d82e9e2b0880f963f53482de39", "generation_seconds_batch": 21.30017559591215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.158614158630371, "target_z": 3.468749934558732, "ce": 5.184661865234375, "genuineness": 4.545003414154053, "identity": 0.6794682741165161, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e74e0287e0f53b19df5d2614751cc1ed478f0f3a15934b5bae7bb19e17042076.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "e7b55ce6b46754b89de834858b248303a312760511e99cf11fa289d03bd18f61", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "95ddff567472f612a96156fdcea67a0e430e9ade7c64f61edebd48977ddd9a95", "generation_seconds_batch": 19.71491714695003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 4.553219318389893, "genuineness": 4.494794845581055, "identity": 0.6768695116043091, "hypothesis": "la puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e7b55ce6b46754b89de834858b248303a312760511e99cf11fa289d03bd18f61.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "e7cbc8f683b56730b0135f3b4d48ba6e5b7bbe8da5465dff9e5afe14fd9a0f3c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f15786ec8a97a943c0f459a796c7cbbdd9532c71248a8ab5103039df3fe4bcd1", "generation_seconds_batch": 21.873838106985204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3896725177764893, "target_z": 2.04687512571612, "ce": 6.109982967376709, "genuineness": 4.7332844734191895, "identity": 0.3536441922187805, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e7cbc8f683b56730b0135f3b4d48ba6e5b7bbe8da5465dff9e5afe14fd9a0f3c.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "e86ba4b9b7103873f5bd9cf5b3be2bdfc1ec6810059d02475c6f8aaf9a7cee4a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e391041ed4b4d0c6a999e758ca6e8d1a9431642028fa417703cdb4cd89859b9", "generation_seconds_batch": 15.287937131011859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 6.109982967376709, "genuineness": 4.532451152801514, "identity": 0.6494326591491699, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e86ba4b9b7103873f5bd9cf5b3be2bdfc1ec6810059d02475c6f8aaf9a7cee4a.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "e941c6aac36cd250f24b2c39f4ad0493e399f4c4df9280363e40132e9f5cad68", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ac46f0685a2270ca44c3926ee4bb1bfec1b04715474d5afab3e787e11a0730a", "generation_seconds_batch": 20.722915444988757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9360058307647705, "target_z": 4.906249969001505, "ce": 5.391171455383301, "genuineness": 4.909013748168945, "identity": 0.8618679046630859, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e941c6aac36cd250f24b2c39f4ad0493e399f4c4df9280363e40132e9f5cad68.mp3" }, { "id": "heldout-fr-3", "language": "fr", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-3", "key": "e99e7127f66048b16003c5c0837d54c7066dc7b1820a1b66e10cc37258776f95", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8edd2c514a21ca45c8a3420f0b94c4fa38bc38aea7acd0f108228888f8491081", "generation_seconds_batch": 16.469337180955335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4150221347808838, "target_z": 2.093749920781623, "ce": 5.418970584869385, "genuineness": 4.570107460021973, "identity": 0.6712711453437805, "hypothesis": "Unquin a déplacé la petite chaise bleue elle était ici près de la grande bibliothèque nous la remettrons auprès le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e99e7127f66048b16003c5c0837d54c7066dc7b1820a1b66e10cc37258776f95.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62fa6b081f2e8382eac064019cf496ea4d6f2577549f1e60689642933eec2524", "generation_seconds_batch": 15.295423352974467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09894880652427673, "target_z": -0.3398437521526733, "ce": 6.372091293334961, "genuineness": 4.595211505889893, "identity": 0.5318834781646729, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Es stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "ea4399052b857f5587091c9e6f0faf4a9b2a4d4a8851400f9d3b3b5204a379cd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed1bb7fd637ccd07f648406fb6eaa8cc9063741afff91e6126778a5561a098d6", "generation_seconds_batch": 19.761636762996204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5248711109161377, "target_z": 2.2968752083787747, "ce": 6.38003396987915, "genuineness": 4.821148872375488, "identity": 0.3973235487937927, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ea4399052b857f5587091c9e6f0faf4a9b2a4d4a8851400f9d3b3b5204a379cd.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "ea6cdd49fce8d3f6a8cf7f9992e17a484445ea42b1a23355b57f150c90dce3dd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce4abbed65684b58fc4e2abcebcd97892fe2feb38bc6024f5282fc028a492cf4", "generation_seconds_batch": 21.703686247929, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2064030170440674, "target_z": 5.406250134326814, "ce": 5.871703147888184, "genuineness": 4.337893962860107, "identity": 0.35724562406539917, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ea6cdd49fce8d3f6a8cf7f9992e17a484445ea42b1a23355b57f150c90dce3dd.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "eab9473c52733e289b1bc866f3b837e85f61aa1055437b5cf10bce144959bd84", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9d42d0c37667714c6839b7621c19772a033a0b4bea7b0ea0cd8dec20d8b6128d", "generation_seconds_batch": 21.26267921400722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9896159172058105, "target_z": 3.1562498312304137, "ce": 5.295859336853027, "genuineness": 4.356721878051758, "identity": 0.5813027620315552, "hypothesis": "Yo mensaje a Diego después de que me fuera, lo leí dos veces y guardé el teléfono, dime cuándo podemos hablar.", "wer": 0.15, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/eab9473c52733e289b1bc866f3b837e85f61aa1055437b5cf10bce144959bd84.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "eb1b09cacaae8a0d4abc00a248e4ca8d91aa842b94f50802ae0036f2faca95fa", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c97f75c3de6d8cbbd2601377688f4394a2094fc8007f643931b33840821280fd", "generation_seconds_batch": 20.304166220943443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5164210796356201, "target_z": 2.2812499827786135, "ce": 5.967014789581299, "genuineness": 4.444586753845215, "identity": 0.5503270030021667, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/eb1b09cacaae8a0d4abc00a248e4ca8d91aa842b94f50802ae0036f2faca95fa.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "eba5a6a5bc1b6a345c11c22835e743bd3234fbf69fee565d2b6796c0522581fe", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6b87cdd56451792553e8fc50583b93a2081f74748bfda947a3ccc95fe0ebd0b", "generation_seconds_batch": 25.519694881979376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.088104248046875, "target_z": 5.187500061996991, "ce": 5.816103935241699, "genuineness": 4.645420074462891, "identity": 0.6866398453712463, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/eba5a6a5bc1b6a345c11c22835e743bd3234fbf69fee565d2b6796c0522581fe.mp3" }, { "id": "heldout-fr-2", "language": "fr", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-2", "key": "ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdc3eb53987f2d42a5f64b01fe8e9cbff7ad9656fde152035652df43e6715188", "generation_seconds_batch": 16.418740987894125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.285362958908081, "target_z": 3.703125232488716, "ce": 6.09409761428833, "genuineness": 4.645420074462891, "identity": 0.7846303582191467, "hypothesis": "La route tourne à gauche après le pont. Continue, jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "ec16fbcc9b61d6083ab64b2bf1bbbdc09e809e04f521347423a765b792bbce67", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "806878272dc649298d839f0d834e3090ca0aab176ef875fdd1c386e3f3311a39", "generation_seconds_batch": 23.77136810205411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6587553024291992, "target_z": 0.6953125094717625, "ce": 6.0305562019348145, "genuineness": 4.808597087860107, "identity": 0.5852624177932739, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ec16fbcc9b61d6083ab64b2bf1bbbdc09e809e04f521347423a765b792bbce67.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "ec2a0e9a8514feeb352de1c1c738c2c9b67e30e2c391b87c572cc641391fee9d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea9450921a857e863a06d306c4cf256b6ae28a006580b392aa65d1df87060021", "generation_seconds_batch": 20.81701773207169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.302262783050537, "target_z": 3.7343752428215473, "ce": 5.458683967590332, "genuineness": 4.557555198669434, "identity": 0.7116022706031799, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ec2a0e9a8514feeb352de1c1c738c2c9b67e30e2c391b87c572cc641391fee9d.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "ec400f4c5ebe3a19f66e720c8879e216c9b21b922df6584d757a18ae4298f3ed", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bcc28179e6c8f281509da4bc15386d16fdc9324660ddc35160054a191709bf60", "generation_seconds_batch": 22.97298427403439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5612990856170654, "target_z": 6.062499910448791, "ce": 5.772419452667236, "genuineness": 4.356721878051758, "identity": 0.14163407683372498, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ec400f4c5ebe3a19f66e720c8879e216c9b21b922df6584d757a18ae4298f3ed.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "ec6f8b8abdde33d8bc90f15e73cabc0df2e36f56cc014bf3d3aba5305dab099b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b763d83bf1ae3e7368a3a65d2d52bc153b4cc617f3cfa6d8f3b049df8a586673", "generation_seconds_batch": 21.655887729953974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5642099380493164, "target_z": 4.218750182546695, "ce": 5.919358730316162, "genuineness": 4.482243061065674, "identity": 0.3895564079284668, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ec6f8b8abdde33d8bc90f15e73cabc0df2e36f56cc014bf3d3aba5305dab099b.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "ee2c10bd87af7a04a16972928016d24b3d0d3c331f6c8cee797c94796dc45487", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21ecd286d9d9f259a30e66a720f1e1cc503038433fc152bb3388b8ca33ee1ea3", "generation_seconds_batch": 21.66639742802363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16337937116622925, "target_z": -0.22070311531297018, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.2958826422691345, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ee2c10bd87af7a04a16972928016d24b3d0d3c331f6c8cee797c94796dc45487.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "ee3305f2d18c18f13370bbe8e315066c7024fb1ff7b1e6651623961a877efc28", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "55ff8233071d5d3fce0004c435655467a062eb39dfcf9e49c9dbaec42bfecbff", "generation_seconds_batch": 16.359595753950998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 6.038498878479004, "genuineness": 4.758388519287109, "identity": 0.5983754396438599, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ee3305f2d18c18f13370bbe8e315066c7024fb1ff7b1e6651623961a877efc28.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "ee6e0dadc6533978fcd01b819120c7d6a218ac027fbbda09ddd9a13dbab88398", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b53cbc4e389611f655c3104a732426a01defc2ae0c9b46440709b438cb6aed5b", "generation_seconds_batch": 15.786097209900618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9727160930633545, "target_z": 3.1249998208975818, "ce": 5.839932441711426, "genuineness": 4.6956281661987305, "identity": 0.7553020715713501, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ee6e0dadc6533978fcd01b819120c7d6a218ac027fbbda09ddd9a13dbab88398.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "ef4406e5613b5d99811c23dfa3c1cdfda932670c829f72875f8d028dbd06d102", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59668560083c3b23dbe204ce64321908dcec082b43251359fd07d78d9ed55484", "generation_seconds_batch": 24.200999881024472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3276124000549316, "target_z": 3.78125003788705, "ce": 6.23706579208374, "genuineness": 4.68307638168335, "identity": 0.7747000455856323, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ef4406e5613b5d99811c23dfa3c1cdfda932670c829f72875f8d028dbd06d102.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "eff79165f3790ea74d19e92aba042021520fb2c204f5a764bddd806d6d9e6dac", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b06b4e322be10bc804a3772e57e8e0aa335a61317b68c78fc49bde527e4ccab", "generation_seconds_batch": 19.768059963011183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8515067100524902, "target_z": 4.7499999173373455, "ce": 5.299830436706543, "genuineness": 4.595211505889893, "identity": 0.6881582140922546, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/eff79165f3790ea74d19e92aba042021520fb2c204f5a764bddd806d6d9e6dac.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "f0211097ddd773745df71ac86fb1932eeafbd0e56963bd0b29629f27f679b59d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4694673d327dd8255cbca79ea28b882a6157c60216d6372e4d17b8c29f9d99c", "generation_seconds_batch": 14.7830396220088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9727160930633545, "target_z": 3.1249998208975818, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.7010862827301025, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f0211097ddd773745df71ac86fb1932eeafbd0e56963bd0b29629f27f679b59d.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "f03ae1fe452dd47868627a182c3ee956590aabba1eead5b59c41e0dd25514ca7", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ac4cc08c94588975263692f47f66d7a60813f1dba15c415ae38a950b5691891", "generation_seconds_batch": 15.9742321530357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.747197151184082, "target_z": 6.406250024109941, "ce": 5.103249549865723, "genuineness": 4.243753433227539, "identity": 0.11151061952114105, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f03ae1fe452dd47868627a182c3ee956590aabba1eead5b59c41e0dd25514ca7.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "f0940d1f7a7317005656e830a3f42e8d008955473d0cf7230abdb7e5235bba88", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2649c69c7bf2d3eba55df4d3e9858e9dc1cb2989f7dccccbf24c47149becb90c", "generation_seconds_batch": 17.424021094106138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2600131034851074, "target_z": 3.6562499965557227, "ce": 6.086154937744141, "genuineness": 4.507347106933594, "identity": 0.6366138458251953, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f0940d1f7a7317005656e830a3f42e8d008955473d0cf7230abdb7e5235bba88.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "f0e82f234bbeb50aa8f9ab795f2bcd99e2d8f0efb11e767ac3ba86cb0eedd863", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bee79fccb2d6c6e854e00a35c58df9b35f04ee9501f867041b59f5d4acf78ee4", "generation_seconds_batch": 21.53121063800063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7601542472839355, "target_z": 0.8828125714687534, "ce": 6.197352409362793, "genuineness": 4.2249250411987305, "identity": 0.358264684677124, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f0e82f234bbeb50aa8f9ab795f2bcd99e2d8f0efb11e767ac3ba86cb0eedd863.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "f100e68dfc65dd701257138323cc27bcc494dc113bfe1dfe0984f833ef1d78d2", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c4d725f52c06f3aee7e99ce933542be101528d0be6c7e359a1bb80a1aba030c", "generation_seconds_batch": 21.466921393061057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8544175624847412, "target_z": 2.9062501894352497, "ce": 6.1894097328186035, "genuineness": 4.934117794036865, "identity": 0.8223235607147217, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f100e68dfc65dd701257138323cc27bcc494dc113bfe1dfe0984f833ef1d78d2.mp3" }, { "id": "heldout-es-0", "language": "es", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-0", "key": "f18647993a5e1529befc3688fe566be7faecd0f4672f9080c9b406e7fbe0bc9b", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33a5df54f034406b5c275d34757105923d5b0a0d85845b5156adf60c400f138c", "generation_seconds_batch": 16.60087605204899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.964266300201416, "target_z": 3.1093750361649115, "ce": 5.526196479797363, "genuineness": 4.532451152801514, "identity": 0.6610511541366577, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f18647993a5e1529befc3688fe566be7faecd0f4672f9080c9b406e7fbe0bc9b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "f21898995fd718fcd99986135cb09629f772edca00f00c8c8f536c9eea09f05c", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05e0711c428062a18473c8ee63207d612ee7fc7e2afcf219af1d9175810ac29b", "generation_seconds_batch": 23.25455799791962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9360058307647705, "target_z": 4.906249969001505, "ce": 4.904682636260986, "genuineness": 4.557555198669434, "identity": 0.5691214799880981, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f21898995fd718fcd99986135cb09629f772edca00f00c8c8f536c9eea09f05c.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba622f958e03f22ffc2ea7cb2824baa4fbe60e04eaee56e4b9102d1c863ba5f8", "generation_seconds_batch": 16.27601595898159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22120842337608337, "target_z": -0.11376954820230219, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.7164402604103088, "hypothesis": "Ton message est arrivé après mon départ, je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "f21d009498b43a5ba66da5a2a0e8080d1478f37ce11018fd2e6450b5144d5875", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ea7215c41eb179c32607fd4265601210a57bc74c91f627e268b37f43a14c6cbb", "generation_seconds_batch": 22.628989787888713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5811097621917725, "target_z": 4.2500001928795275, "ce": 5.395142555236816, "genuineness": 4.331617832183838, "identity": 0.6298002004623413, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f21d009498b43a5ba66da5a2a0e8080d1478f37ce11018fd2e6450b5144d5875.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "f2d8a8770bb5299be5fac253e0ca181475c2485dd5cdcd8d065414b3a647265a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "37b9971049f82911c06727c46c65ca0193b3776fa7c4201a55043c1b9ec196d7", "generation_seconds_batch": 22.11656731099356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1163647174835205, "target_z": 3.3906251291603975, "ce": 5.39911413192749, "genuineness": 4.394378662109375, "identity": 0.44571784138679504, "hypothesis": "Uh the door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f2d8a8770bb5299be5fac253e0ca181475c2485dd5cdcd8d065414b3a647265a.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "f311f1311033f0fce143d0d489531fce7d71a0baf6cf749374de29a5e4d5df65", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2ab57344ef122567abd2da03f24eb8569a4dcf55a96f471cbe385b1204ae8958", "generation_seconds_batch": 24.33557234692853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13486091792583466, "target_z": -0.27343750774962383, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.20068791508674622, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f311f1311033f0fce143d0d489531fce7d71a0baf6cf749374de29a5e4d5df65.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "f361d132db7d3df91aa0d2ef4833d50d0cec999c0ceffbe09e3e5511e4b34c33", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e7f5b1249ebc6a3b1a9a3b74685bf3d6ef3a68a35776fbcf7a6df8623566aba", "generation_seconds_batch": 17.187170448014513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1895031929016113, "target_z": 5.375000123993981, "ce": 5.605623245239258, "genuineness": 4.607763767242432, "identity": 0.6485792398452759, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f361d132db7d3df91aa0d2ef4833d50d0cec999c0ceffbe09e3e5511e4b34c33.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "f3afac1489ca08889651243524873917fd712e893a18c05e62e342d560ca27ba", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f70b57c198e9bd8b09b3c33d363b801dc79ec37a7e1d08755f19534166061ef5", "generation_seconds_batch": 21.935666568926536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.088104248046875, "target_z": 5.187500061996991, "ce": 5.411027908325195, "genuineness": 4.68307638168335, "identity": 0.7409828901290894, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f3afac1489ca08889651243524873917fd712e893a18c05e62e342d560ca27ba.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "f3fd613cbd42a01224c300d33880747d5a5d07d9852f208c21ca49d244ed7656", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29ffcc430ce6ec0425f3bd46bca8b0b47747b447fec65580cca112401845763c", "generation_seconds_batch": 21.618246876983903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6418554782867432, "target_z": 0.6640624991389307, "ce": 6.284721851348877, "genuineness": 4.632867813110352, "identity": 0.6192674040794373, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f3fd613cbd42a01224c300d33880747d5a5d07d9852f208c21ca49d244ed7656.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "f43d345ebf5832c3d2eeff48c9ea215e2d662cd9b470506de88aa988e2ef27eb", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "438a017b29c60b63b972099a94ad8169afdf2e0e3ab13872099cb18f684967bf", "generation_seconds_batch": 23.25455799791962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0036051273345947, "target_z": 5.0312500103328315, "ce": 5.260117053985596, "genuineness": 4.607763767242432, "identity": 0.5855830907821655, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f43d345ebf5832c3d2eeff48c9ea215e2d662cd9b470506de88aa988e2ef27eb.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "f45e3cba6da714b216f0a65ee0cbe7f9d7c4a41f8d050144dd6b3876293d5411", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "128faf2d6f5ad39f654c0a8cee81c75c07f1f3545b02ed036667180f2aa155da", "generation_seconds_batch": 20.461271884967573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1361751556396484, "target_z": 1.578124970723643, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.3814501166343689, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f45e3cba6da714b216f0a65ee0cbe7f9d7c4a41f8d050144dd6b3876293d5411.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "f5adf0fdf470cf69c25956e8993966e41306926e6f7c19aed65c6b591611165d", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bee19060616752cf71554d424848465f24a914528ae416e719c4f3c2bb1a2e1d", "generation_seconds_batch": 24.33557234692853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3086121678352356, "target_z": 0.04785153699082147, "ce": 6.4515180587768555, "genuineness": 4.645420074462891, "identity": 0.3555600345134735, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f5adf0fdf470cf69c25956e8993966e41306926e6f7c19aed65c6b591611165d.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "f5b727181600860ffdb91e318ad89c8130befa0cb4630477a6023ebb14598790", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e193b8bd8219103300a2bd320d24f5bf46f2633ad63c6ca57cc28b1ed999a7c", "generation_seconds_batch": 15.631258054985665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.319162607192993, "target_z": 3.7656252531543792, "ce": 5.613565921783447, "genuineness": 4.2751336097717285, "identity": 0.2818734049797058, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f5b727181600860ffdb91e318ad89c8130befa0cb4630477a6023ebb14598790.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "f5b75faee85a8f2103d5214c722ccbe76fd79f1bf8b111a2d405c586be06f7c7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47433dbbba1393980d340d7c95364259e263aaed93e3944d867916b53dacad14", "generation_seconds_batch": 21.445718046976253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7221295833587646, "target_z": 0.8124999380030091, "ce": 6.173524379730225, "genuineness": 4.262581825256348, "identity": 0.6494054794311523, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f5b75faee85a8f2103d5214c722ccbe76fd79f1bf8b111a2d405c586be06f7c7.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "f5cee96a43e83ceeee09396195aabdf878492b9a1331e4beb8abe979dc4dd46b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a10aa3be61dd8c6558b789065233cbbbf9e855c75036998c3ef669383188aef2", "generation_seconds_batch": 22.38210699299816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6587553024291992, "target_z": 0.6953125094717625, "ce": 5.95112943649292, "genuineness": 4.218649387359619, "identity": 0.30784034729003906, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f5cee96a43e83ceeee09396195aabdf878492b9a1331e4beb8abe979dc4dd46b.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-0", "key": "f5d63ad2e8f1ca87ba51a3e8c7728f522466d40169649b602d2519ff5fe99959", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2defe18ebe6a01fcfa39e52222a221a121ef22ae3ec38897fc9e032e1570b6a3", "generation_seconds_batch": 22.848197911982425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1235003471374512, "target_z": 1.554687573190892, "ce": 6.157639026641846, "genuineness": 4.6203155517578125, "identity": 0.80255526304245, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f5d63ad2e8f1ca87ba51a3e8c7728f522466d40169649b602d2519ff5fe99959.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "f666812d1c86c119bbec5a36537312b865f6fe46a989f4f168a952ff0f5e171b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "66ea2ccc2059b49d54244c294116a775dd50846e191818caa33d8673494610b0", "generation_seconds_batch": 20.7737854529405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820617914199829, "target_z": 2.8437501687695863, "ce": 5.808161735534668, "genuineness": 4.457139015197754, "identity": 0.29829642176628113, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f666812d1c86c119bbec5a36537312b865f6fe46a989f4f168a952ff0f5e171b.mp3" }, { "id": "heldout-nl-2", "language": "nl", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-2", "key": "f751a52b3e9d584b0baab64d6bcc8d2e23bdbf4221fad2f9de5b3c7eeb683aea", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1d51f818fe0729fe2b0c11b08bcc476f1b89a429b310d5eaaaf6220f35ed94c4", "generation_seconds_batch": 22.98461381997913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6119985580444336, "target_z": 6.156249941447286, "ce": 5.335572719573975, "genuineness": 4.017816066741943, "identity": 0.27310025691986084, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine auto-hek. Ik ga het aan de auto.", "wer": 0.2857142857142857, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f751a52b3e9d584b0baab64d6bcc8d2e23bdbf4221fad2f9de5b3c7eeb683aea.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "f755c906f77bc694dbe57f363a3400d34f766f2e967a460453acbdb795a3b895", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7531718a2153174b0588346bdeae8ffe5547a35a5fffacf4a0abca821b204ad2", "generation_seconds_batch": 21.849317504907958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1404001712799072, "target_z": 1.5859375835237237, "ce": 5.895530700683594, "genuineness": 4.432034492492676, "identity": 0.5433681607246399, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f755c906f77bc694dbe57f363a3400d34f766f2e967a460453acbdb795a3b895.mp3" }, { "id": "heldout-es-4", "language": "es", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-4", "key": "f755f549c0ca3493160779598d720a5a6fe883498b004b051a463bfbc9a2db29", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74ed7b2ebf30f262bba57c2969ed5b8ddd6e3aa6a5eeea1f170a8c42b8bad35e", "generation_seconds_batch": 20.698475447949022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3698620796203613, "target_z": 3.8593752841528746, "ce": 5.168776512145996, "genuineness": 4.344170093536377, "identity": 0.3381064236164093, "hypothesis": "Escribí el número en el sobre, dénelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f755f549c0ca3493160779598d720a5a6fe883498b004b051a463bfbc9a2db29.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "f78bdaf51e110b02d6f7b55d801554009575cac51749604a9002ad937828672b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61be7a5a7bcb55bae3a16697e0041dbc87d5028533fc415644f319e822acc088", "generation_seconds_batch": 20.903771981946193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5079712867736816, "target_z": 2.265625198045943, "ce": 6.022613525390625, "genuineness": 4.319066047668457, "identity": 0.45974448323249817, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f78bdaf51e110b02d6f7b55d801554009575cac51749604a9002ad937828672b.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "f79461abe180de66f3327a4fd35e319f54dbbb7ea5d7faa938ab152c5c40fe54", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b8b6dbff4c1f12e736791e54c7070b41065615ccbe39c684d3e6827058bcb9df", "generation_seconds_batch": 20.11870645696763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7192189693450928, "target_z": 2.656250106772595, "ce": 5.172747611999512, "genuineness": 4.268857479095459, "identity": 0.2702927887439728, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f79461abe180de66f3327a4fd35e319f54dbbb7ea5d7faa938ab152c5c40fe54.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "f79f58f4679d68f99419b76e168243b5b8f5eb40cb7d729a4354a84bf475c8a4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "435a92851de1c1df070378fcb2c4e8519686fe7ac472b41802804f068854e81d", "generation_seconds_batch": 20.90114910400007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45806995034217834, "target_z": 0.3242187469862574, "ce": 5.792276382446289, "genuineness": 4.7081804275512695, "identity": 0.6358715295791626, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f79f58f4679d68f99419b76e168243b5b8f5eb40cb7d729a4354a84bf475c8a4.mp3" }, { "id": "heldout-fr-1", "language": "fr", "sentences": [ "Les clés sont sur la table de la cuisine.", "J’ai regardé dans le tiroir... puis près de la fenêtre.", "Prends-les quand tu partiras." ], "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-1", "key": "f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11305f2d87ee646813f14961ad9a3aafecf1625aa1cdf799103945cdc527673d", "generation_seconds_batch": 17.22775938094128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11690486967563629, "target_z": -0.3066406161740395, "ce": 6.181467056274414, "genuineness": 4.557555198669434, "identity": 0.789274275302887, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "f83d1ace6ea9c6a25e6a04ce6116e171281b3fe1621cf29041d7de20c89e0319", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4f2455d04c1d3fe62493bd796537eedfa34cf39fa7162ded9eb3f27f34fc711", "generation_seconds_batch": 22.346747720032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9840767979621887, "target_z": 1.2968749879450296, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.24168801307678223, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f83d1ace6ea9c6a25e6a04ce6116e171281b3fe1621cf29041d7de20c89e0319.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f4dfa9e60ea7c71c189f347128d4e0ff9055032f6c8041177faf8ad8cbc4c64", "generation_seconds_batch": 15.790036327089183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0432262420654297, "target_z": 1.4062501343268135, "ce": 6.109982967376709, "genuineness": 4.545003414154053, "identity": 0.6840642094612122, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "f975574b3aa2a18f4b1d152c45c1ca78d1437dcddf56f9bc2c7ea11fdb6b5187", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a223fa8c652d0b8d57386e3643795326aa89cf6074f06498cabdb1d2b1512dc", "generation_seconds_batch": 20.3020143910544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6347198486328125, "target_z": 2.5000000551084365, "ce": 5.982900142669678, "genuineness": 4.331617832183838, "identity": 0.5872523784637451, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f975574b3aa2a18f4b1d152c45c1ca78d1437dcddf56f9bc2c7ea11fdb6b5187.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "f98349d8a9c551fb6aa12cb6d7ce0b723b703ca72f1ee5397f754a4d16daa5ce", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7232ab52df61530fb1dfc490de6b6a3c7b6240af64eb81976a443a55509a3b0f", "generation_seconds_batch": 20.77002086106222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.716308355331421, "target_z": 4.500000275542182, "ce": 5.863759994506836, "genuineness": 4.896461486816406, "identity": 0.7726696133613586, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f98349d8a9c551fb6aa12cb6d7ce0b723b703ca72f1ee5397f754a4d16daa5ce.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "f9a8327ecdd52a4d3d7220781af1994754ba0d8f1837181c1634efc0bbab6af7", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9816437cb53b6af71a3a9dba30ff09209e6ce0b97f2b7fc8d28d1ef164e0fbd3", "generation_seconds_batch": 21.450998093932867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5135104656219482, "target_z": 4.1250001515482, "ce": 4.978152275085449, "genuineness": 4.030367851257324, "identity": 0.5618298053741455, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f9a8327ecdd52a4d3d7220781af1994754ba0d8f1837181c1634efc0bbab6af7.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "f9c8e3229660be77089fdec256c8865f3eb65cf7817dc8e0b1d009765f9935e5", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1f1ae37b54fc67020fdd777dc02c766367759872acca1603a6bdca5d43a08bc1", "generation_seconds_batch": 16.438179277000017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5443992614746094, "target_z": 6.031249900115959, "ce": 4.679309368133545, "genuineness": 4.13078498840332, "identity": 0.5738144516944885, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f9c8e3229660be77089fdec256c8865f3eb65cf7817dc8e0b1d009765f9935e5.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "f9d827be97432ea8d5f42674ac878d767967d148c6925cd1ffc8ba6fbc12dd77", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "042536cf9e06fc7335e2027ab9258c9377e0a9c0526d10a2ca5685852697e440", "generation_seconds_batch": 20.280788411037065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.341601610183716, "target_z": 5.656250216989468, "ce": 5.403085231781006, "genuineness": 4.645420074462891, "identity": 0.6682387590408325, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f9d827be97432ea8d5f42674ac878d767967d148c6925cd1ffc8ba6fbc12dd77.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "f9e98e01f77a6dae3bafa6c56c219a3875c6060306d964efebe0f486f555deaf", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31e1299d961715f88222655d81dd1a1489e8a974482b1bd7b0b1761287f595eb", "generation_seconds_batch": 21.232956737978384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5642099380493164, "target_z": 4.218750182546695, "ce": 5.982900142669678, "genuineness": 4.457139015197754, "identity": 0.4888538122177124, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/f9e98e01f77a6dae3bafa6c56c219a3875c6060306d964efebe0f486f555deaf.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "fa9d777028e5bda6f25df69abe8f2fc9b5cfeb499641bda2605afa3d8f84c2a4", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88bf5212ebe3ddf39ad4985b277ed715cc8defb73b3bbdd8933f2b5e790b62f1", "generation_seconds_batch": 16.165209794067778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9896159172058105, "target_z": 3.1562498312304137, "ce": 5.80021858215332, "genuineness": 4.381826400756836, "identity": 0.5864408016204834, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fa9d777028e5bda6f25df69abe8f2fc9b5cfeb499641bda2605afa3d8f84c2a4.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "fac1a0406041c0b6c6a036561dc09f25a2c539e91bb387a71d4548bd78e73b49", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c17e8bf0b4a489af589628396f539f39b540a9e7a79415dc070947b844a0ce46", "generation_seconds_batch": 19.919784166966565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.121903896331787, "target_z": 5.2500000826626545, "ce": 4.243455410003662, "genuineness": 4.457139015197754, "identity": 0.6828797459602356, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fac1a0406041c0b6c6a036561dc09f25a2c539e91bb387a71d4548bd78e73b49.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "faec44677bec2ba7543754caa5a1ba5d34d0ef51574d07aa7a951f481a7b4ebd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe58d4ab6a6fc1a7b50a0401ad3d11e7088dcc80a83f3e04112cef73d2604eb0", "generation_seconds_batch": 21.703686247929, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9867053031921387, "target_z": 5.0, "ce": 5.998785495758057, "genuineness": 4.444586753845215, "identity": 0.5726104974746704, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/faec44677bec2ba7543754caa5a1ba5d34d0ef51574d07aa7a951f481a7b4ebd.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "faf0c3faf13ea4e036ecc5b258e9cf69897cf16d15d4bd051b2a7c126afe37c0", "bucket": "emo_Fatigue_Exhaustion", "phase": "wording", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93299cc7da85210b59f653460e2f9f62fa1bf8201582659b5b5d53696c937c1e", "generation_seconds_batch": 15.776844699052162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6503053903579712, "target_z": 0.6796875043053466, "ce": 5.839932441711426, "genuineness": 4.143336772918701, "identity": 0.5599609613418579, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/faf0c3faf13ea4e036ecc5b258e9cf69897cf16d15d4bd051b2a7c126afe37c0.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-0", "key": "fb14ba21974dab611dec841ff8f3fe6f64eba9473f4ba80768d62f4ff201d1a1", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The door is still open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5f68f43b44a5e93905ea4e4e240db3e57e448f6d3532b59278671ed2988e095", "generation_seconds_batch": 20.81924850004725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8024037480354309, "target_z": 0.9609374870839602, "ce": 6.062326908111572, "genuineness": 4.118232727050781, "identity": 0.3096364736557007, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fb14ba21974dab611dec841ff8f3fe6f64eba9473f4ba80768d62f4ff201d1a1.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-0", "key": "fb2f2603cdbb51ebe9ce03bcd6b385ed7944f66d4f9f14279c0693721ed7fa2b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36ead6b9e12c7be08d59a445d69dab102748eb4a70a80bbc40ca04df45c0a67c", "generation_seconds_batch": 21.445718046976253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1953245401382446, "target_z": 1.6875000068885546, "ce": 6.062326908111572, "genuineness": 4.532451152801514, "identity": 0.7253617644309998, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fb2f2603cdbb51ebe9ce03bcd6b385ed7944f66d4f9f14279c0693721ed7fa2b.mp3" }, { "id": "heldout-en-4", "language": "en", "sentences": [ "I wrote the number on the envelope.", "Read it carefully... and check the last two digits.", "Call me when you have a moment." ], "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-4", "key": "fc7c5647f18b5ba0eac74a37a27b6d564502d9a958f8a9dad14ad10f757c6016", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "906ea64a50270c73a1151a07fe9401be90adc92f4bb3e3f7abd3177443edda3e", "generation_seconds_batch": 21.803113210015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9925267100334167, "target_z": 1.3124999931114454, "ce": 5.02977991104126, "genuineness": 4.18099308013916, "identity": 0.37381017208099365, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fc7c5647f18b5ba0eac74a37a27b6d564502d9a958f8a9dad14ad10f757c6016.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "fc80354e67310640edcbbc39914568c2bc68795f711def14a57003e60cd53e4b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d23c6eafa72e456a3c00942b99594d5af995d46b5e6978616e7c3b1ae303a2d3", "generation_seconds_batch": 19.589108846965246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966670036315918, "target_z": 2.9843749948335843, "ce": 5.279973983764648, "genuineness": 4.482243061065674, "identity": 0.6204591989517212, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fc80354e67310640edcbbc39914568c2bc68795f711def14a57003e60cd53e4b.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-0", "key": "fc9a2036c45b91001316076bb362cac936784d14f87a54b64aae9b27135c6535", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "18a990b008e5b3961405c399a0d106f4c9b8c2127f91f5cc2f2e8cea90cf9806", "generation_seconds_batch": 17.26740084704943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1361751556396484, "target_z": 1.578124970723643, "ce": 5.748591423034668, "genuineness": 4.250029563903809, "identity": 0.5090271234512329, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fc9a2036c45b91001316076bb362cac936784d14f87a54b64aae9b27135c6535.mp3" }, { "id": "emo_Fatigue_Exhaustion-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-es-1", "key": "fcf638143694a193547408e64147313a301022bc98675f74a6e6d7837f1eb285", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60a54662f2ec58a5c2b09e0484070af14ace04119580b583bded46a54a2258c6", "generation_seconds_batch": 20.00661881803535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3896725177764893, "target_z": 2.04687512571612, "ce": 5.522225379943848, "genuineness": 4.7834930419921875, "identity": 0.513849675655365, "hypothesis": "Me he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fcf638143694a193547408e64147313a301022bc98675f74a6e6d7837f1eb285.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-0", "key": "fd0b54af6235fd546577b8d2e676c38d54f443f1ffa234d618ffcab069de56e7", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "719b5f3364a5690b60df9be6fc208094817a2bb67027dfc10913716c8ecee5fe", "generation_seconds_batch": 22.338222955004312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8784529566764832, "target_z": 1.1015625335817034, "ce": 6.109982967376709, "genuineness": 4.65797233581543, "identity": 0.6309643983840942, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fd0b54af6235fd546577b8d2e676c38d54f443f1ffa234d618ffcab069de56e7.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "fd462cfe58fc2c26d7274968e7974ee15613268bb883516a3761bfcaac131c1e", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62461c238f4e0e948f3814c4cdada2493b444c35760add2068d5d0d0ab3c5ec2", "generation_seconds_batch": 21.158034638967365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2753406763076782, "target_z": -0.013671851966395757, "ce": 6.372091293334961, "genuineness": 4.632867813110352, "identity": 0.38481783866882324, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fd462cfe58fc2c26d7274968e7974ee15613268bb883516a3761bfcaac131c1e.mp3" }, { "id": "emo_Fatigue_Exhaustion-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-nl-1", "key": "fd63db7f32901764b72f522f23f056ea6275ba947b5395eb1f7df2c7d0c5f5dd", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0f0059d5436248e68185b904369799756e70524ced5459ccd276919ba2028eb0", "generation_seconds_batch": 22.86245118000079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5781989097595215, "target_z": 6.093749920781622, "ce": 5.816103935241699, "genuineness": 4.306513786315918, "identity": 0.0863078385591507, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. Hoe kunnen we daar samen in kijken?", "wer": 0.16666666666666666, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fd63db7f32901764b72f522f23f056ea6275ba947b5395eb1f7df2c7d0c5f5dd.mp3" }, { "id": "emo_Fatigue_Exhaustion-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-de-1", "key": "fe76734a4ac6828850b28d083fb873be491046000061959fe902fafd39b94781", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6a6549d282159b8b31b2bedb692f5768f47e4bbc615e8ff14b2bce0a2cca3d4e", "generation_seconds_batch": 21.684136152034625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0065157413482666, "target_z": 3.1874998415632456, "ce": 5.522225379943848, "genuineness": 4.381826400756836, "identity": 0.6493292450904846, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fe76734a4ac6828850b28d083fb873be491046000061959fe902fafd39b94781.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "fedc85705acf76a949b673f3373a0a2faaebd74472695065a4a7ce1075051143", "bucket": "emo_Fatigue_Exhaustion", "phase": "heldout", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7815e601f5e98334a4d8e719da7189a3d13b5921ca124025ba4bf667f9a88142", "generation_seconds_batch": 16.415260565001518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3305230140686035, "target_z": 1.9374998691174636, "ce": 6.165581703186035, "genuineness": 4.287685871124268, "identity": 0.5978116989135742, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/fedc85705acf76a949b673f3373a0a2faaebd74472695065a4a7ce1075051143.mp3" }, { "id": "emo_Fatigue_Exhaustion-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-en-1", "key": "ff7316670e7719e51f44dcea99ae668041d6c9ee7da8132678fb2aaab9df473a", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] I found the little box.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] It was beside the old window.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01621b9f9020f50adff3fab35671f8fc04ef136438bd550eb24ec0dc48b95901", "generation_seconds_batch": 15.377039915067144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0770258903503418, "target_z": 1.468750154992477, "ce": 6.070269584655762, "genuineness": 4.7834930419921875, "identity": 0.388165682554245, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ff7316670e7719e51f44dcea99ae668041d6c9ee7da8132678fb2aaab9df473a.mp3" }, { "id": "emo_Fatigue_Exhaustion-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Fatigue_Exhaustion-fr-1", "key": "ff7852d86c4dff332859a976a6dd7ece698c60641ccd0e62f44dd9859261e29b", "bucket": "emo_Fatigue_Exhaustion", "phase": "grid", "candidate": "manual-1711f3012766", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Embody exhaustion as a systemic drain, where the voice sounds hollowed out and brittle. Prioritize texture over volume.\nSCRIPT:\n(Begin with a breathy onset, implying the lungs are incapable of a full, robust inhalation before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle vocal fry or rasping texture on key consonants to signify deep physical strain.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the last phrase with a fragile, almost cracking quality, as if the vocal apparatus is on the verge of breaking.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48dec76ca03110bc3c74cb05fc1c5f4b221f2bf3342ec66edaa0241e3aed912f", "generation_seconds_batch": 15.150018464075401, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1319501399993896, "target_z": 1.5703123579235627, "ce": 6.0305562019348145, "genuineness": 4.959221839904785, "identity": 0.6359766721725464, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fatigue_Exhaustion/ff7852d86c4dff332859a976a6dd7ece698c60641ccd0e62f44dd9859261e29b.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "d628d37f0f2bbd50a5666db8e9fca218000455fdb778e680b01be1e7390f4c6f", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4739135503768921, "target_z": 0.3535156592275054, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.5731421113014221, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/dad0d4c56e2bb754af33a23e.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "329ac302018936eebcb8ae2691d5c8a01c198adb2de83444e35c7ae95604f849", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.482621431350708, "target_z": 2.21874996211295, "ce": 6.125868320465088, "genuineness": 4.632867813110352, "identity": 0.6940319538116455, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/fe74377c4e7137add7b79556.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "3d92d5ab216ef561cd993089131854737b3bbd3144caf7f16f7f44353bac2a01", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.840428352355957, "target_z": 1.0312500103328317, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.480739951133728, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/385c734e40a1c96b7af305a1.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "ece03dffbf3f50e7cefa752d8503a54854f3ec2941399f06ba588bec8fc8fa77", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8953527808189392, "target_z": 1.1328125439145351, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.5910923480987549, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/6dff41d7a2d761221168f1c4.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "0ab9208089644573604f4ee0130e866c97f66a20dc1111a9964e0981acd4f20f", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5079712867736816, "target_z": 2.265625198045943, "ce": 6.260893821716309, "genuineness": 4.65797233581543, "identity": 0.6138240098953247, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/d14771e510cb366048af3cb7.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "94557257f75a270d427e861a7649535554c965440ab6863f5b601f2254514077", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.047451138496399, "target_z": 1.4140625266931488, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.6091328859329224, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/540546da4ff430b2872b190f.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "3898d2aa89a66a1c6010314bf85286c1e8ead5f85589dd553b12ad4c31e26d82", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2122243642807007, "target_z": 1.7187500172213863, "ce": 6.252951145172119, "genuineness": 4.7834930419921875, "identity": 0.5257860422134399, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/5fe926d9a217c002db549206.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-0-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "248e2136eef110004aa5ce934f8d7ac0d977d2e0126a083081eed26512f80512", "task_id": "emo_Fatigue_Exhaustion-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5755703449249268, "target_z": 2.3906247985097795, "ce": 6.340320587158203, "genuineness": 4.65797233581543, "identity": 0.7169508934020996, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/9e68fe636f3a05d23eed6288.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "c5dd0c8c005c759c3e214d73675add8e7f588d411da980ba19aadb32ceaef3b8", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1211298257112503, "target_z": -0.29882811359083156, "ce": 6.284721851348877, "genuineness": 4.193545341491699, "identity": 0.5630494356155396, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/134435608d4662aa6c4350fc.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "9a49becaaff24aebad6f843e157d5260b1b3fcc92fd3743e713911042faad331", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13380467891693115, "target_z": -0.27539063339542585, "ce": 6.403861999511719, "genuineness": 4.645420074462891, "identity": 0.5608289241790771, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/046720a7ba13ecd782e85115.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "9ed21933cb78a3cf185ae16fda063c370601377eb928a7f798112cc977a8db1e", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37885206937789917, "target_z": 0.17773440621376277, "ce": 6.372091293334961, "genuineness": 4.570107460021973, "identity": 0.6658207178115845, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/185060e7592a96050d8f6831.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "4c91e1c753959db6804353c4024b46518968f18ee02c8c5f8815cf1d11dd80b5", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08627393841743469, "target_z": -0.36328125990229715, "ce": 6.268836498260498, "genuineness": 4.262581825256348, "identity": 0.5825868844985962, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/de05035ec89cbf67555a43b8.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "56233f810c9b72a6ab547cb0cdc32d2bcc30c19e023b16ede1619964135fe145", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02606832981109619, "target_z": -0.47460939415879233, "ce": 6.324435234069824, "genuineness": 4.281409740447998, "identity": 0.47592610120773315, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/664715e526c5470944505266.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "6e4772c8272b6075a63463f7e4d306ebccd0448ebde7ee48c03d67d376fc15b3", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06198045611381531, "target_z": -0.4082031222015247, "ce": 6.213237762451172, "genuineness": 4.105680465698242, "identity": 0.6702540516853333, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/dcff6ca6a337d48ffcf31f73.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "e315bb5296002748fdaa57d11681e2888a8551d4e017d29b524c7506bbee61d2", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2843186855316162, "target_z": 0.0029296746915939025, "ce": 6.300607204437256, "genuineness": 4.65797233581543, "identity": 0.19260218739509583, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/eea6d57a6ab6d4bde6ec40a0.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-de-1-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "2e01b7652969f5e88604a921f82042899462c7fc042cd563c540cef7e6725011", "task_id": "emo_Fatigue_Exhaustion-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06303669512271881, "target_z": -0.40624999655572275, "ce": 6.268836498260498, "genuineness": 4.15588903427124, "identity": 0.36765730381011963, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/de/5dfeae93b9633a7bd53510f0.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "620acc9b4a4967129a0e812dc9baa5134a8d1b8eaadfac81dd012f623bad8a59", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6355180740356445, "target_z": 0.6523438003725551, "ce": 6.332377910614014, "genuineness": 4.356721878051758, "identity": 0.2530188262462616, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/4fbb71f3720a9a195557f9fa.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "9b20f7300985a9e3b73acd4b5e6fcf275ad3b14a45dac65be9aee7ecf99dd578", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3751552104949951, "target_z": 0.17089842512212855, "ce": 6.1894097328186035, "genuineness": 4.293961524963379, "identity": 0.29026132822036743, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/4fdf6cba3149bead101d5fb2.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "0112426d7f32a47cfc023a24e92aeb41e992c31e9011cf8736ad5c19f3e8fcbd", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21803972125053406, "target_z": -0.11962889758548999, "ce": 6.260893821716309, "genuineness": 3.9927117824554443, "identity": 0.31762072443962097, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/aa2c1640cab6e2b5ecdd82f3.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "9edb2df6e9dc8a78770dd16f10e449ec729b69db2ea7a4ebf3ab83aa51f0eef7", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18080730736255646, "target_z": -0.18847655593434645, "ce": 6.133810997009277, "genuineness": 4.2374773025512695, "identity": 0.27743518352508545, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/ee6e09222c55f3b7716836c7.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "5017f3184d4b258db95f8399c65fcf7c91f92eb2c8190bf6678786436ea06643", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5341191291809082, "target_z": 0.4648437383755642, "ce": 6.117925643920898, "genuineness": 4.024092197418213, "identity": 0.21138471364974976, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/e0c2043b382457bfae728233.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "ae3176ca0dc4f58014d018c97283a33a261283480c1dd2be9a10549468ed5705", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4834196865558624, "target_z": 0.37109376248550513, "ce": 6.23706579208374, "genuineness": 4.13078498840332, "identity": 0.4381771385669708, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/7c2d872eb8ce2c47c8e34108.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "fc23162a5836497f47fe7033345fb9ac70bca7f867052295a6d5b85960aac610", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5277817249298096, "target_z": 0.4531250396091886, "ce": 6.1020402908325195, "genuineness": 4.143336772918701, "identity": 0.3483617603778839, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/4af0d06a92498740b1919b40.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-0-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "1485ea94618d2208b2eebcb84a6300ee6596e47355aafe23e2b6ef2a843ebc28", "task_id": "emo_Fatigue_Exhaustion-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6481928825378418, "target_z": 0.6757811979053063, "ce": 6.165581703186035, "genuineness": 4.20609712600708, "identity": 0.21432146430015564, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/d02fe6c01665774d38b2c511.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "2cdfbbc70a2a4deb2dd8d28d0773a9b1b7210d30a7486cb4dd7c5bb75919caad", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21566317975521088, "target_z": -0.124023437177099, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.36829525232315063, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/d1aea66e86b74b452122a912.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "0e8931a018d6183d00bc6f39c944552f1cea12f61afcd37eefb7c123aa4bf515", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20932574570178986, "target_z": -0.13574219105191093, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.3546132445335388, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/75096a9e28d539fa65a6621c.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "8443d13957bc4864e6ba63f3fc3982c14232fd036687a7f7108129c4a95b8555", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21249446272850037, "target_z": -0.12988281411450497, "ce": 6.324435234069824, "genuineness": 4.582659721374512, "identity": 0.31175148487091064, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/6e53e993f31f14209534c524.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "8b54bd559449d24ed2d521cdec371be63bfd3ce5a386449df175e22fe2999961", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2087976336479187, "target_z": -0.13671874009770285, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.5556110143661499, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/b5b6d21a6dc9defc479ba620.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "94318dbc9f3dc76b8f680418645c867ccd0dcb4aa9dc3acbf6066816d144e09c", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1813354194164276, "target_z": -0.18750000688855453, "ce": 6.372091293334961, "genuineness": 4.400654315948486, "identity": 0.3223896026611328, "hypothesis": "I found the little box. It was beside the old's window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/5105ab06af126fe14eeaba6b.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "41fc50663bc8dfa06b6b97b78a2fd5d1bcfc3f953b769268fac3b8600afec619", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3086121678352356, "target_z": 0.04785153699082147, "ce": 6.38797664642334, "genuineness": 4.65797233581543, "identity": 0.40355366468429565, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/3f731c31c2e2c1b232890ed7.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "4ccd34326e59f63c9c4c97d873b56527b24bbb64255428e476efb60a2d224697", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1507045030593872, "target_z": -0.24414062306259404, "ce": 6.221180438995361, "genuineness": 4.287685871124268, "identity": 0.3688356876373291, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/6b77e4f72c347f8a46b15d12.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-en-1-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "13ec920bfbb38066bd825e3f865bb857db85e05c909f386a3bb33df34923b935", "task_id": "emo_Fatigue_Exhaustion-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1485920250415802, "target_z": -0.248046874354198, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.41542744636535645, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/en/e38bcb32f06d2d2ed9be1bf4.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "b35c209ea5dedc65f1fc0617288f865f67b68944d071db28c60b42244f6b8584", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8713173866271973, "target_z": 2.9375001997680816, "ce": 5.804190158843994, "genuineness": 4.532451152801514, "identity": 0.4942071735858917, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/07628450a351212742845099.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "22524ae7bf09443a6ea434d45501955fe089e7fea9d72b7f91e52e5ae9128515", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0516760349273682, "target_z": 1.4218749190594842, "ce": 6.086154937744141, "genuineness": 4.519899368286133, "identity": 0.5726639628410339, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/35b8d75b9f17f439f0c2ac88.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "a78bd9c5f7747f16d8c3818cf6dfe2acd08ab5ea91570e5aaa9f0553aa687436", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5333209037780762, "target_z": 2.3124999931114454, "ce": 6.038498878479004, "genuineness": 4.419482707977295, "identity": 0.7007639408111572, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/0834fb10f5c21f95f52aa12a.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "3cdf757aee66d7fc3203f779a95201add847bf7a51b2a58693ee406eb385dfef", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3136231899261475, "target_z": 1.906249858784632, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.6617738008499146, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/3e09e8ea6738de079beb195e.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "17a78c914d2814a0f25f9ead02a0e9c428fe0c227c0846ddcb3fa86796592557", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43694519996643066, "target_z": 0.28515628917865393, "ce": 5.982900142669678, "genuineness": 4.268857479095459, "identity": 0.6519211530685425, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/dc424df7645dfdaa47c4ca40.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "2f2efad6c0a9b921a5b4fec37c0269046643b4a1764109e8171734c67b65b14a", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2087976336479187, "target_z": -0.13671874009770285, "ce": 6.070269584655762, "genuineness": 4.093128204345703, "identity": 0.5818453431129456, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/134c5ff313756ee127da8cac.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "fac72639b052613934079e9b11c17d8277e9e586f95d6368743d8e7224118c24", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5383440852165222, "target_z": 0.4726562409587722, "ce": 6.022613525390625, "genuineness": 4.2249250411987305, "identity": 0.6086034774780273, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/f141f9230ef2b367e0d3967a.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-0-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "984ccabc3e827a9cf1b26c3d469dbe25e36a7a5fd73d701b37b2346350c4f508", "task_id": "emo_Fatigue_Exhaustion-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.21644926071167, "target_z": 1.7265624095877217, "ce": 5.871703147888184, "genuineness": 4.174716949462891, "identity": 0.637222409248352, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/bc33f463e64a3e8dfeb9a21b.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "12d61210c6900f1d3747312e048f41d5aa91609134fb0d4a6e102b35a7baa336", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6207306981086731, "target_z": 0.6249999862228909, "ce": 6.046441555023193, "genuineness": 4.7081804275512695, "identity": 0.6673516035079956, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/3678935f8a414c5eb016cbab.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "afdeabb178479dcad9ced67d764504c4a26608b8ed6da44097cc4a2a7f12020d", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16866055130958557, "target_z": -0.2109375146381784, "ce": 6.070269584655762, "genuineness": 4.6705241203308105, "identity": 0.8579299449920654, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/bcf804335ee14e0f3aa80e10.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "ccdd7a63d4dec4bf470d15c3caa344f1fc58e4f26b59ef5ec3efd4934146dcb7", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4179328680038452, "target_z": 0.24999997244578184, "ce": 6.141753673553467, "genuineness": 4.720732688903809, "identity": 0.7030829191207886, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/7b19daa5246bd6913525904a.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "43d139e1a87f7c1ece5748c5a2bc10d1d722bccc490d7d300518fa8382896325", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10423000156879425, "target_z": -0.33007812392366337, "ce": 6.078212261199951, "genuineness": 4.519899368286133, "identity": 0.6750555038452148, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/980a14841c06efb3f630d558.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "d8c42b372df9d35fe683fb9e17766043e5e0aba5a141b3b7add3a4d635186324", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7094547748565674, "target_z": 0.7890625404702579, "ce": 6.09409761428833, "genuineness": 4.758388519287109, "identity": 0.7008033990859985, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/21517c14e22b482184b6a7a9.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "2871895b32b04055bcb773c1d4cf87f18aa5dc490585d5735bf7b4fe1b48c75e", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3643226623535156, "target_z": 1.9999998897831273, "ce": 6.173524379730225, "genuineness": 4.758388519287109, "identity": 0.5269898176193237, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/22365b0cf959f47b96a9ed9b.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "79b70f62590bc24fb5e273cb235f71daa2547f49356ad053fd7cd658e54dc7fb", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28167811036109924, "target_z": -0.0019530980915838285, "ce": 6.086154937744141, "genuineness": 4.6956281661987305, "identity": 0.6943225860595703, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/a6ef0e05ef1fe42587627586.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-es-1-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "daf891bd87dbf71c76f788ab7c4f90e19775ced5af4ab4483a0487631bace339", "task_id": "emo_Fatigue_Exhaustion-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8024037480354309, "target_z": 0.9609374870839602, "ce": 6.078212261199951, "genuineness": 4.796044826507568, "identity": 0.6779048442840576, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/es/a2bf6253c0c887902a775bb0.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "8d6491229252f68ba43f15db39da2e3ea9c47d5eef9723a657f0ef15d0485888", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4739135503768921, "target_z": 0.3535156592275054, "ce": 6.117925643920898, "genuineness": 4.720732688903809, "identity": 0.6128017902374268, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/69f9bd55da3e9be3423a1a70.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "803e0ef7a0c0aea29783f31a57a8afbfe88a1a5f4623b2ba6b808748542f85b4", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1699748039245605, "target_z": 1.6406249913893067, "ce": 6.086154937744141, "genuineness": 4.6956281661987305, "identity": 0.8461108207702637, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/9b5377cbf60be56b05b59a49.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "27c25a9c9373e1bc27c8ba919155dc06d21601a070fa81194094adbf8e8cc421", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6291806101799011, "target_z": 0.6406249913893068, "ce": 6.165581703186035, "genuineness": 4.469690799713135, "identity": 0.8632656335830688, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/11696aec6aef59e2d546b476.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "b77457331078dd235a7b24062b5ea4b721a9c54fbf551a4a21ce2a796c72ffeb", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1235003471374512, "target_z": 1.554687573190892, "ce": 6.181467056274414, "genuineness": 4.595211505889893, "identity": 0.8568853139877319, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/430f8b9b69ecdade20a45355.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "c03e3495e5e06b96d90fb6732add794bc0a5e6acc452f11e3fb32c2d4856e87a", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8214160799980164, "target_z": 0.9960938038168323, "ce": 5.9431867599487305, "genuineness": 4.356721878051758, "identity": 0.6958664059638977, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/1c576bddac9b878178a5dc19.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "e4cf06c163703766e73524b56ffccfdaa8a9cd4cc9fc8c07b895553af008bebe", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6693177223205566, "target_z": 0.7148438210382186, "ce": 5.998785495758057, "genuineness": 4.444586753845215, "identity": 0.6992267370223999, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/eb0e263c8a3cdd531996bcab.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "a1253e37ce821c7abfeffc956b211352ae003d7057288ef644d4ccdab2985692", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7559292316436768, "target_z": 0.8749999586686728, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.7502714395523071, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/016841ead4262ba68222a0f0.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-0-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "9a4b8a46dc7fd38f8785c2d25052031510cf0f97ce95e5ae2e58edba92143de8", "task_id": "emo_Fatigue_Exhaustion-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7390294075012207, "target_z": 0.8437499483358409, "ce": 6.086154937744141, "genuineness": 4.519899368286133, "identity": 0.6363332271575928, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/58caac6ee8c6df95d7d0e014.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "aa5cf6da9878b0743ef876b040b0d685af1fd9480812fa4905efc7ed8707f649", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18344789743423462, "target_z": -0.18359375559695057, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.7764697074890137, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/2cd385d2667a9a8cc07c92ef.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "1c64d9156bcbe04ab32288214462fcdc1a0664a5a8d37b6c9e45eb308e96ba51", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2629238367080688, "target_z": 1.8125000482198819, "ce": 5.974957466125488, "genuineness": 4.65797233581543, "identity": 0.681833028793335, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/504ec5fb7416a548bb8646c7.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "aa4fa77e78b3e0c9dcce9a37cfeec5bb544d9659c63958650ee81add4aa2c4ff", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3941675126552582, "target_z": 0.20605468674656435, "ce": 6.165581703186035, "genuineness": 4.6705241203308105, "identity": 0.7786016464233398, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/9ec8ca73f5d970b2c652348f.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "622426a49b3b51e479830ec02fca3a4537e78004f8b51b76e92d1a77cd30f826", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5425690412521362, "target_z": 0.4804687435419801, "ce": 5.9431867599487305, "genuineness": 4.250029563903809, "identity": 0.6788955926895142, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/9b6846cfd42c418f3a7aa623.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "16d1ecd03885c5e4e50d7c08d23b521aba6cab619bedde22e0264cd517ee8dbf", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18291977047920227, "target_z": -0.18457033219696065, "ce": 6.260893821716309, "genuineness": 4.362998008728027, "identity": 0.779241681098938, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/b6214e1e0fb4be2d18fbf292.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "a424c10baba48d4ef3cf7e688467f6db5ded73640560daed6572246478930566", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4475075602531433, "target_z": 0.3046874905282375, "ce": 6.109982967376709, "genuineness": 4.68307638168335, "identity": 0.8045724630355835, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/0655ba8b680eb4fbb61c7fa1.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "c07ad28e28252db39556f3ad9f57e750f565a9078bd215439809b8d2ac5da6df", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5024319887161255, "target_z": 0.4062500241099409, "ce": 5.974957466125488, "genuineness": 4.645420074462891, "identity": 0.7325088977813721, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/3a6901061de45f48d6e4fbf1.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-fr-1-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "48bbf463b781a78ae487e015ba0399ed76de645981900294313b743247774370", "task_id": "emo_Fatigue_Exhaustion-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2690032422542572, "target_z": -0.025390605841207687, "ce": 6.062326908111572, "genuineness": 4.6203155517578125, "identity": 0.6255881786346436, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/fr/b89644e4942b21648c12acfc.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "a8b940bfbcd1506563fa02544fb2dd5c1e391003c2009606e0534c5581ba8fe4", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3347480297088623, "target_z": 1.9453124819175442, "ce": 5.9431867599487305, "genuineness": 4.319066047668457, "identity": 0.34849148988723755, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/5a9a2d9debcd54bb3a040d28.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "fee3cc5f2efe4358c731a3edfa62816e6811e980c3bbcb2b5a14037f243655df", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4741716384887695, "target_z": 2.2031251773802794, "ce": 6.117925643920898, "genuineness": 4.482243061065674, "identity": 0.6346963047981262, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/c264bbe3da4d933d0d40b748.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "d766da855cf6c05c4daee456a2068e8cac64c814abca3aaca5ed89b9b720b9ef", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7179046869277954, "target_z": 0.8046875456366738, "ce": 6.0305562019348145, "genuineness": 4.080576419830322, "identity": 0.6324582695960999, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/836d3caff70d65507da64f29.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "487cd38a62e216f8f1525294c05325cb077c0fe42b330b8dbc5392931c421650", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7094547748565674, "target_z": 0.7890625404702579, "ce": 5.903473377227783, "genuineness": 4.068024158477783, "identity": 0.6026120781898499, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/fba238a021b704e71265dd44.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "544a39938fb154b70bb206601a2ec71270ecd91a943d2e73e6abe984a30759c8", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.267148733139038, "target_z": 1.820312440586217, "ce": 6.165581703186035, "genuineness": 4.3881025314331055, "identity": 0.6203609704971313, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/547857f38504fe43eaee2d30.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "f391a6f4112f6edb0dbfb7a9db9980068579021f3a1c82d50576a7d27e1d17de", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1066005229949951, "target_z": 1.52343756285806, "ce": 5.967014789581299, "genuineness": 4.18726921081543, "identity": 0.5683097839355469, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/ea77ef6d18a2065ce6b28567.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "c3c519c6e85287ed433d97bd07a2a5482d754621d98207aca3600e740b6c83ce", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37251460552215576, "target_z": 0.1660155972305145, "ce": 6.2767791748046875, "genuineness": 4.375550270080566, "identity": 0.4149709939956665, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/81641b792062cf6e0d666dbc.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-0-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "0148dd426c6cb90064b80d7fefd96f98e87e34b1b1d354b03ffc7f0f18883b92", "task_id": "emo_Fatigue_Exhaustion-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7192189693450928, "target_z": 2.656250106772595, "ce": 5.903473377227783, "genuineness": 4.306513786315918, "identity": 0.4029562175273895, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/2f92e747b9ea3341da66cc35.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1701-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "6c70ec7aa23f3963647e9b5162328c2b5704dce624f2f8ed1a50708600297955", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6587553024291992, "target_z": 0.6953125094717625, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.6163414716720581, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/65f0fe2d7677ef1f07a2d6fb.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1701-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "68152d7e709e6e8cb17fa1054e63d50640a440186c296b7109cc740a9793c20a", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6312930583953857, "target_z": 0.6445311875724745, "ce": 6.117925643920898, "genuineness": 4.306513786315918, "identity": 0.506420373916626, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/ab8f03eef7b3b29f145d5e70.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1701-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "2c10546a10632c58877c78bc845b18f9214fc3b4ca2fc9da92c30679af247836", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.233349084854126, "target_z": 1.7578124199205534, "ce": 6.125868320465088, "genuineness": 4.375550270080566, "identity": 0.6899201273918152, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/25dcf6fcb46c2470b4be7fe6.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1701-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "9f77c328fa26110915bf7ec650b9924c6141c559cafdb6f429efaad017c5ab5d", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9883017539978027, "target_z": 1.3046874905282375, "ce": 6.086154937744141, "genuineness": 4.369274139404297, "identity": 0.6386492252349854, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/409c286174e6394297d59f95.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1702-scale0.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "7a65a0c9e4444f9ad9eeb001c968d3ae4185f312bec40837634bffd6ecefc3c8", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1784247159957886, "target_z": 1.6562499965557227, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.7104282379150391, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/381b0f0da1e0fcc719fc4a28.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1702-scale0.5", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "e6786218b899cb998c71c28bc47cdb4ee051360eda4985b0ffdda9554bb07199", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2901279926300049, "target_z": 0.013671851966395757, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.7427052855491638, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/a52e35a1e1e5fe98be53947a.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1702-scale0.75", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "79bd15fbb08b8f6d9389a4e1cab03efdd9d7bbc160801ba06d22c79e22d44dbf", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6685194969177246, "target_z": 2.5625000757741, "ce": 6.260893821716309, "genuineness": 4.570107460021973, "identity": 0.7252969741821289, "hypothesis": "Ik heb het klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/b92a90277b1faadd98296cd7.mp3" }, { "key": "original-emo_Fatigue_Exhaustion-nl-1-seed1702-scale1.0", "bucket": "emo_Fatigue_Exhaustion", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "directions": [ "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 128, "seconds_generated": 10.24, "ended": true, "contract_sha256": "c9bca36a07c8d21f34f5ffb1aedb339bab40435592559cdc2c784c7758099cf1", "mp3_sha256": "25df4692ec7f7438ea8cd9a666f91eb338f60f706880cde3b1259820cec7ea59", "task_id": "emo_Fatigue_Exhaustion-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Intense Fatigue Exhaustion. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9333773255348206, "target_z": 1.203124956946534, "ce": 6.268836498260498, "genuineness": 4.400654315948486, "identity": 0.5078482627868652, "hypothesis": "Ik heb het klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fatigue_Exhaustion/nl/476ee39c763a9574b46e9149.mp3" } ], "source_standard_audio_unchanged": true }