The merged parent used in these specialist comparisons is now released as Humaneness Voice Large 1.6 Alpha: 1.5 + final RealSpeech rank 4, merged once. Apply only the selected new bucket adapter. Do not reload either ancestor.
1.5 Original model · 1.6 merged model · Complete context manuals for humans and agents
Read 1.5 context manual · Read 1.6 + adapter context manual. Exact prompts, CFG, adapter scales and failed gates are retained. New model/documentation contributions: CC BY 4.0; existing upstream and gated specialist terms remain applicable.
The original grid used generic GENERAL/SCRIPT directions at CFG1. It did not systematically use target-specific manual winners. The new study freezes the actual rank-4 manual wording, preserves every literal word, seed, reference, adapter and frame budget, then independently varies CFG and adapter strength. The previous recordings and conclusions remain below.
Ranking:100% requested EARS emotion/style head, standardized using frozen training statistics; low-pole targets reverse the sign. Formal/casual contrasts average the desired head and negative opposite head. CE and genuineness are diagnostics. Higher target z means stronger desired delivery, not a human rating. More CFG is not automatically better.
Selection:20 original-text outcomes per configuration select wording, CFG and scale. Fifty additional unseen-text reference pairs test the frozen choices. A recommended adapter must improve against both the same-CFG no-adapter control and the best manual-only setting. Quality gates: per-take WER≤15%, mean WER≤10%, valid/terminated fraction≥90%, paired identity change≥−0.05 over50pairs. Failed outcomes stay visible. Language-cluster bootstrap intervals use only five fixed reference voices; findings across72targets remain exploratory.
Five languages: EN/DE/FR/NL/ES; original seeds1701/1702; reference187frames/14.96seconds. CFG1/1.25/1.5/2/2.5/3/4/5 × bucket strength0/0.5/0.75/1. CFG4/5 are stress conditions, not presumed improvements. No-reference use of these bucket recommendations has not been validated.
Taxonomy:S_MONO means Monologue, S_TECH means Teacher/Didactic, VOLT means Volatility. The two corrected style recipes and17dimension/contrast recipes are new searches, not historical manual winners.53other targets reuse directly applicable manual recipes.
Best tested agent route: Use manual-only configuration; no clear qualifying incremental adapter gain. Bucket scale 0.0, CFG 2.5.
| Held-out condition | n | Target z↑ | Raw head | CE↑ | Genuine↑ | Voice↑ | WER↓ | Valid | QA |
|---|---|---|---|---|---|---|---|---|---|
| standard | 50 | -0.440 | 0.052 | 6.237 | 4.415 | 0.584 | 0.014 | 0.980 | pass |
| manual | 50 | 0.532 | 0.647 | 6.035 | 4.191 | 0.551 | 0.019 | 0.980 | pass |
| adapter | 50 | 2.579 | 1.900 | 5.739 | 3.794 | 0.509 | 0.060 | 0.880 | fail |
| matched_no_adapter | 50 | 2.304 | 1.731 | 5.872 | 3.922 | 0.510 | 0.037 | 0.960 | fail |
Incremental adapter gain versus same-CFG control: 0.275 z;95% cluster interval [-0.19946293770941095, 0.7436352500497889]. Versus best manual-only: 2.047 z. Manual-only versus standard: 0.972 z.
| Scale | CFG | Target z | CE | Genuine | WER | Provisional QA |
|---|---|---|---|---|---|---|
| 0.0 | 1.0 | -0.458 | 6.131 | 4.475 | 0.000 | True |
| 0.5 | 1.0 | -0.441 | 6.158 | 4.401 | 0.008 | True |
| 0.75 | 1.0 | -0.440 | 6.139 | 4.391 | 0.013 | True |
| 1.0 | 1.0 | -0.327 | 6.113 | 4.383 | 0.000 | True |
| 0.0 | 1.25 | -0.378 | 6.149 | 4.455 | 0.006 | True |
| 0.5 | 1.25 | -0.392 | 6.120 | 4.421 | 0.003 | True |
| 0.75 | 1.25 | -0.380 | 6.117 | 4.425 | 0.000 | True |
| 1.0 | 1.25 | -0.281 | 6.096 | 4.409 | 0.005 | True |
| 0.0 | 1.5 | -0.392 | 6.089 | 4.468 | 0.005 | True |
| 0.5 | 1.5 | -0.094 | 6.095 | 4.470 | 0.013 | True |
| 0.75 | 1.5 | -0.216 | 6.056 | 4.428 | 0.008 | True |
| 1.0 | 1.5 | -0.171 | 5.990 | 4.404 | 0.036 | True |
| 0.0 | 2.0 | 0.245 | 6.083 | 4.393 | 0.055 | False |
| 0.5 | 2.0 | 0.556 | 6.008 | 4.364 | 0.043 | False |
| 0.75 | 2.0 | 0.433 | 5.997 | 4.316 | 0.005 | True |
| 1.0 | 2.0 | 0.619 | 5.869 | 4.248 | 0.022 | True |
| 0.0 | 2.5 | 0.766 | 6.015 | 4.324 | 0.014 | True |
| 0.5 | 2.5 | 1.272 | 5.887 | 4.187 | 0.036 | True |
| 0.75 | 2.5 | 1.406 | 5.920 | 4.190 | 0.068 | False |
| 1.0 | 2.5 | 1.197 | 5.868 | 4.208 | 0.013 | True |
| 0.0 | 3.0 | 1.627 | 5.906 | 4.151 | 0.014 | False |
| 0.5 | 3.0 | 1.924 | 5.925 | 4.122 | 0.087 | True |
| 0.75 | 3.0 | 2.370 | 5.818 | 3.958 | 0.058 | False |
| 1.0 | 3.0 | 2.135 | 5.729 | 4.001 | 0.028 | True |
| 0.0 | 4.0 | 3.022 | 5.861 | 3.947 | 0.089 | False |
| 0.5 | 4.0 | 2.923 | 5.737 | 3.931 | 0.021 | True |
| 0.75 | 4.0 | 3.016 | 5.637 | 3.864 | 0.081 | False |
| 1.0 | 4.0 | 3.364 | 5.627 | 3.800 | 0.073 | False |
| 0.0 | 5.0 | 3.413 | 5.728 | 3.877 | 0.095 | False |
| 0.5 | 5.0 | 3.391 | 5.637 | 3.799 | 0.072 | False |
| 0.75 | 5.0 | 3.632 | 5.637 | 3.739 | 0.171 | False |
| 1.0 | 5.0 | 3.868 | 5.441 | 3.632 | 0.079 | False |
direct_manual_recipe
{
"id": "manual-e2b016e601f8",
"general": "Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.",
"inline": [
"Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.",
"Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.",
"End with the sound catching in the throat, a desperate, high-tension release."
],
"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"
}Exact machine-readable comparison · Agent tool recommendations
Intense Fear. Base: 1.5 Alpha + merged real-speech rank4; new adapter: rank32. Every row is a matched seed/text/reference test. Scale zero disables the new adapter; all other scales are applied absolutely, never compounded.
Adapter training data: {"en": 37, "nl": 54, "fr": 56, "es": 47, "de": 55}. All available accepted languages were pooled, globally shuffled, for three epochs. Peak LR 2e-05 at the end of the first-epoch warmup, then cosine decay. All original optimizer/RNG checkpoints remain saved.
Taxonomy: S_MONO is monologue, not monotone; VOLT is volatility, not volume. No claim is made that a classifier score alone proves the audible performance.
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 20 | 0.324 ± 0.021 | 6.152 ± 0.150 | 4.388 ± 0.229 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 20 | 0.330 ± 0.028 | 6.180 ± 0.104 | 4.401 ± 0.219 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 20 | 0.325 ± 0.020 | 6.161 ± 0.144 | 4.356 ± 0.236 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 20 | 0.322 ± 0.021 | 6.137 ± 0.158 | 4.317 ± 0.209 | 0.00% ± 0.00 |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.303 ± 0.005 | 6.245 ± 0.128 | 4.211 ± 0.237 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.305 ± 0.006 | 6.265 ± 0.033 | 4.195 ± 0.239 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.304 ± 0.005 | 6.213 ± 0.145 | 4.208 ± 0.175 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.299 ± 0.010 | 6.187 ± 0.081 | 4.190 ± 0.117 | 0.00% ± 0.00 |
| Prompt / seed | Merged base · no new LoRA | Rank32 × 0.5 | Rank32 × 0.75 | Rank32 × 1.0 |
|---|---|---|---|---|
| Seed 1701 The door is still open. I put your coat on the chair. Tell me when you are ready. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (Intense Fear. 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. (Intense Fear. 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. | Target 0.303 · CE 6.30 · Genuine 4.38 · WER 0.0% | Target 0.298 · CE 6.28 · Genuine 3.99 · WER 0.0% | Target 0.298 · CE 6.09 · Genuine 4.01 · WER 0.0% | Target 0.290 · CE 6.19 · Genuine 4.13 · WER 0.0% |
| Seed 1702 The door is still open. I put your coat on the chair. Tell me when you are ready. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (Intense Fear. 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. (Intense Fear. 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. | Target 0.296 · CE 6.05 · Genuine 3.86 · WER 0.0% | Target 0.309 · CE 6.25 · Genuine 3.99 · WER 0.0% | Target 0.304 · CE 6.09 · Genuine 4.12 · WER 0.0% | Target 0.300 · CE 6.09 · Genuine 4.07 · WER 0.0% |
| Seed 1701 I found the little box. It was beside the old window. We can look inside together. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (Intense Fear. 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. (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together. | Target 0.307 · CE 6.29 · Genuine 4.31 · WER 0.0% | Target 0.311 · CE 6.30 · Genuine 4.43 · WER 0.0% | Target 0.310 · CE 6.30 · Genuine 4.37 · WER 0.0% | Target 0.312 · CE 6.28 · Genuine 4.34 · WER 0.0% |
| Seed 1702 I found the little box. It was beside the old window. We can look inside together. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (Intense Fear. 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. (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together. | Target 0.304 · CE 6.33 · Genuine 4.29 · WER 0.0% | Target 0.302 · CE 6.23 · Genuine 4.37 · WER 0.0% | Target 0.304 · CE 6.37 · Genuine 4.34 · WER 0.0% | Target 0.292 · CE 6.19 · Genuine 4.21 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.326 ± 0.020 | 6.303 ± 0.081 | 4.586 ± 0.147 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.323 ± 0.023 | 6.267 ± 0.137 | 4.460 ± 0.141 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.318 ± 0.019 | 6.273 ± 0.098 | 4.462 ± 0.125 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.323 ± 0.013 | 6.289 ± 0.162 | 4.387 ± 0.124 | 0.00% ± 0.00 |
| Prompt / seed | Merged base · no new LoRA | Rank32 × 0.5 | Rank32 × 0.75 | Rank32 × 1.0 |
|---|---|---|---|---|
| Seed 1701 Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (Intense Fear. 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. (Intense Fear. 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. | Target 0.327 · CE 6.23 · Genuine 4.80 · WER 0.0% | Target 0.335 · CE 6.10 · Genuine 4.49 · WER 0.0% | Target 0.325 · CE 6.20 · Genuine 4.47 · WER 0.0% | Target 0.315 · CE 6.09 · Genuine 4.44 · WER 0.0% |
| Seed 1702 Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (Intense Fear. 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. (Intense Fear. 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. | Target 0.355 · CE 6.25 · Genuine 4.53 · WER 0.0% | Target 0.348 · CE 6.21 · Genuine 4.61 · WER 0.0% | Target 0.336 · CE 6.18 · Genuine 4.63 · WER 0.0% | Target 0.342 · CE 6.23 · Genuine 4.38 · WER 0.0% |
| Seed 1701 Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. 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. (Intense Fear. 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. (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.309 · CE 6.40 · Genuine 4.46 · WER 0.0% | Target 0.299 · CE 6.41 · Genuine 4.47 · WER 0.0% | Target 0.322 · CE 6.38 · Genuine 4.40 · WER 0.0% | Target 0.319 · CE 6.42 · Genuine 4.22 · WER 0.0% |
| Seed 1702 Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. 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. (Intense Fear. 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. (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.315 · CE 6.33 · Genuine 4.56 · WER 0.0% | Target 0.310 · CE 6.34 · Genuine 4.27 · WER 0.0% | Target 0.291 · CE 6.33 · Genuine 4.34 · WER 0.0% | Target 0.315 · CE 6.42 · Genuine 4.51 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.317 ± 0.017 | 6.084 ± 0.163 | 4.482 ± 0.128 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.329 ± 0.015 | 6.090 ± 0.062 | 4.485 ± 0.125 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.319 ± 0.017 | 6.148 ± 0.107 | 4.523 ± 0.078 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.312 ± 0.004 | 6.035 ± 0.196 | 4.399 ± 0.296 | 0.00% ± 0.00 |
| Prompt / seed | Merged base · no new LoRA | Rank32 × 0.5 | Rank32 × 0.75 | Rank32 × 1.0 |
|---|---|---|---|---|
| Seed 1701 La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (Intense Fear. 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. (Intense Fear. 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. | Target 0.332 · CE 5.99 · Genuine 4.41 · WER 0.0% | Target 0.341 · CE 6.02 · Genuine 4.34 · WER 0.0% | Target 0.332 · CE 6.17 · Genuine 4.42 · WER 0.0% | Target 0.309 · CE 6.08 · Genuine 4.66 · WER 0.0% |
| Seed 1702 La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (Intense Fear. 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. (Intense Fear. 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. | Target 0.330 · CE 5.92 · Genuine 4.34 · WER 0.0% | Target 0.340 · CE 6.06 · Genuine 4.43 · WER 0.0% | Target 0.326 · CE 6.06 · Genuine 4.58 · WER 0.0% | Target 0.311 · CE 5.81 · Genuine 3.97 · WER 0.0% |
| Seed 1701 J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. 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. (Intense Fear. 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. (Intense Fear. 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. | Target 0.299 · CE 6.28 · Genuine 4.62 · WER 0.0% | Target 0.309 · CE 6.17 · Genuine 4.63 · WER 0.0% | Target 0.325 · CE 6.07 · Genuine 4.51 · WER 0.0% | Target 0.318 · CE 6.28 · Genuine 4.49 · WER 0.0% |
| Seed 1702 J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. 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. (Intense Fear. 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. (Intense Fear. 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. | Target 0.306 · CE 6.14 · Genuine 4.56 · WER 0.0% | Target 0.326 · CE 6.11 · Genuine 4.53 · WER 0.0% | Target 0.294 · CE 6.29 · Genuine 4.58 · WER 0.0% | Target 0.309 · CE 5.97 · Genuine 4.47 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.329 ± 0.006 | 6.116 ± 0.092 | 4.172 ± 0.191 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.353 ± 0.044 | 6.140 ± 0.057 | 4.263 ± 0.196 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.350 ± 0.011 | 6.080 ± 0.196 | 4.313 ± 0.112 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.338 ± 0.027 | 6.138 ± 0.119 | 4.339 ± 0.158 | 0.00% ± 0.00 |
| Prompt / seed | Merged base · no new LoRA | Rank32 × 0.5 | Rank32 × 0.75 | Rank32 × 1.0 |
|---|---|---|---|---|
| Seed 1701 De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (Intense Fear. 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. (Intense Fear. 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. | Target 0.336 · CE 6.08 · Genuine 4.19 · WER 0.0% | Target 0.347 · CE 6.12 · Genuine 4.09 · WER 0.0% | Target 0.366 · CE 5.97 · Genuine 4.16 · WER 0.0% | Target 0.367 · CE 6.13 · Genuine 4.31 · WER 0.0% |
| Seed 1702 De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (Intense Fear. 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. (Intense Fear. 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. | Target 0.333 · CE 6.08 · Genuine 3.90 · WER 0.0% | Target 0.417 · CE 6.08 · Genuine 4.21 · WER 0.0% | Target 0.343 · CE 5.86 · Genuine 4.34 · WER 0.0% | Target 0.354 · CE 5.98 · Genuine 4.15 · WER 0.0% |
| Seed 1701 Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. 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. (Intense Fear. 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. (Intense Fear. 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. | Target 0.323 · CE 6.05 · Genuine 4.34 · WER 0.0% | Target 0.326 · CE 6.15 · Genuine 4.55 · WER 0.0% | Target 0.340 · CE 6.22 · Genuine 4.33 · WER 0.0% | Target 0.309 · CE 6.17 · Genuine 4.37 · WER 0.0% |
| Seed 1702 Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. 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. (Intense Fear. 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. (Intense Fear. 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. | Target 0.326 · CE 6.25 · Genuine 4.26 · WER 0.0% | Target 0.322 · CE 6.21 · Genuine 4.21 · WER 0.0% | Target 0.350 · CE 6.27 · Genuine 4.42 · WER 0.0% | Target 0.321 · CE 6.27 · Genuine 4.53 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.345 ± 0.026 | 6.011 ± 0.088 | 4.489 ± 0.142 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.341 ± 0.019 | 6.138 ± 0.078 | 4.603 ± 0.148 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.334 ± 0.011 | 6.092 ± 0.124 | 4.275 ± 0.442 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.337 ± 0.013 | 6.037 ± 0.107 | 4.269 ± 0.306 | 0.00% ± 0.00 |
| Prompt / seed | Merged base · no new LoRA | Rank32 × 0.5 | Rank32 × 0.75 | Rank32 × 1.0 |
|---|---|---|---|---|
| Seed 1701 La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Fear. 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. (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.360 · CE 6.06 · Genuine 4.48 · WER 0.0% | Target 0.357 · CE 6.05 · Genuine 4.39 · WER 0.0% | Target 0.350 · CE 5.95 · Genuine 4.26 · WER 0.0% | Target 0.357 · CE 5.98 · Genuine 4.03 · WER 0.0% |
| Seed 1702 La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Fear. 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. (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.373 · CE 5.88 · Genuine 4.34 · WER 0.0% | Target 0.357 · CE 6.24 · Genuine 4.71 · WER 0.0% | Target 0.334 · CE 6.08 · Genuine 3.67 · WER 0.0% | Target 0.332 · CE 5.94 · Genuine 4.02 · WER 0.0% |
| Seed 1701 He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Fear. 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. (Intense Fear. 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. | Target 0.318 · CE 6.05 · Genuine 4.44 · WER 0.0% | Target 0.322 · CE 6.14 · Genuine 4.62 · WER 0.0% | Target 0.328 · CE 6.25 · Genuine 4.68 · WER 0.0% | Target 0.329 · CE 6.05 · Genuine 4.66 · WER 0.0% |
| Seed 1702 He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Fear. 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. (Intense Fear. 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. | Target 0.328 · CE 6.05 · Genuine 4.68 · WER 0.0% | Target 0.329 · CE 6.13 · Genuine 4.70 · WER 0.0% | Target 0.325 · CE 6.09 · Genuine 4.49 · WER 0.0% | Target 0.331 · CE 6.18 · Genuine 4.37 · WER 0.0% |