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 5.0.
| Held-out condition | n | Target z↑ | Raw head | CE↑ | Genuine↑ | Voice↑ | WER↓ | Valid | QA |
|---|---|---|---|---|---|---|---|---|---|
| standard | 50 | -0.470 | 0.135 | 6.258 | 4.378 | 0.584 | 0.006 | 1.000 | pass |
| manual | 50 | 0.578 | 0.936 | 5.879 | 4.646 | 0.603 | 0.034 | 0.960 | pass |
| adapter | 50 | 0.488 | 0.868 | 5.772 | 4.532 | 0.605 | 0.020 | 0.980 | pass |
| matched_no_adapter | 50 | 0.578 | 0.936 | 5.879 | 4.646 | 0.603 | 0.034 | 0.960 | pass |
Incremental adapter gain versus same-CFG control: -0.090 z;95% cluster interval [-0.15291015425009538, -0.02666013719074121]. Versus best manual-only: -0.090 z. Manual-only versus standard: 1.048 z.
| Scale | CFG | Target z | CE | Genuine | WER | Provisional QA |
|---|---|---|---|---|---|---|
| 0.0 | 1.0 | -0.214 | 6.093 | 4.523 | 0.005 | True |
| 0.5 | 1.0 | -0.230 | 6.126 | 4.532 | 0.000 | True |
| 0.75 | 1.0 | -0.251 | 6.097 | 4.501 | 0.006 | True |
| 1.0 | 1.0 | -0.215 | 6.160 | 4.467 | 0.000 | True |
| 0.0 | 1.25 | -0.009 | 6.087 | 4.572 | 0.003 | True |
| 0.5 | 1.25 | -0.209 | 6.098 | 4.525 | 0.000 | True |
| 0.75 | 1.25 | -0.091 | 6.072 | 4.528 | 0.000 | True |
| 1.0 | 1.25 | -0.135 | 6.106 | 4.458 | 0.012 | True |
| 0.0 | 1.5 | 0.046 | 6.120 | 4.628 | 0.003 | True |
| 0.5 | 1.5 | -0.023 | 6.017 | 4.549 | 0.003 | True |
| 0.75 | 1.5 | 0.003 | 6.094 | 4.556 | 0.003 | True |
| 1.0 | 1.5 | -0.082 | 6.026 | 4.501 | 0.006 | True |
| 0.0 | 2.0 | 0.253 | 6.065 | 4.671 | 0.003 | True |
| 0.5 | 2.0 | 0.057 | 6.011 | 4.604 | 0.003 | True |
| 0.75 | 2.0 | 0.232 | 5.963 | 4.598 | 0.000 | True |
| 1.0 | 2.0 | 0.155 | 5.977 | 4.571 | 0.003 | True |
| 0.0 | 2.5 | 0.235 | 5.972 | 4.683 | 0.000 | True |
| 0.5 | 2.5 | 0.339 | 5.997 | 4.625 | 0.000 | True |
| 0.75 | 2.5 | 0.294 | 5.948 | 4.584 | 0.003 | True |
| 1.0 | 2.5 | 0.314 | 5.886 | 4.563 | 0.000 | True |
| 0.0 | 3.0 | 0.456 | 5.940 | 4.692 | 0.000 | True |
| 0.5 | 3.0 | 0.418 | 5.884 | 4.633 | 0.006 | True |
| 0.75 | 3.0 | 0.388 | 5.915 | 4.634 | 0.012 | True |
| 1.0 | 3.0 | 0.359 | 5.820 | 4.585 | 0.000 | True |
| 0.0 | 4.0 | 0.533 | 5.863 | 4.661 | 0.008 | True |
| 0.5 | 4.0 | 0.419 | 5.793 | 4.635 | 0.003 | True |
| 0.75 | 4.0 | 0.547 | 5.755 | 4.555 | 0.003 | True |
| 1.0 | 4.0 | 0.417 | 5.678 | 4.536 | 0.014 | True |
| 0.0 | 5.0 | 0.544 | 5.761 | 4.660 | 0.009 | True |
| 0.5 | 5.0 | 0.554 | 5.641 | 4.627 | 0.019 | True |
| 0.75 | 5.0 | 0.460 | 5.619 | 4.569 | 0.003 | True |
| 1.0 | 5.0 | 0.590 | 5.652 | 4.546 | 0.003 | True |
direct_manual_recipe
{
"id": "manual-dbfdc96d1cab",
"general": "Deep genuine sadness; fragile breath, lowered energy and restrained grief rather than a neutral reading. Establish it from the first phrase. Deep genuine sadness; fragile breath, lowered energy and restrained grief rather than a neutral reading. Sustain it through the thought. Deep genuine sadness; fragile breath, lowered energy and restrained grief rather than a neutral reading. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable.",
"inline": [
"Deep genuine sadness; fragile breath, lowered energy and restrained grief rather than a neutral reading. Establish it from the first phrase. Begin with the feeling held back, then let it leak through and become unmistakable.",
"Deep genuine sadness; fragile breath, lowered energy and restrained grief rather than a neutral reading. Sustain it through the thought. Begin with the feeling held back, then let it leak through and become unmistakable.",
"Deep genuine sadness; fragile breath, lowered energy and restrained grief rather than a neutral reading. Keep it audible in the final sentence. Begin with the feeling held back, then let it leak through and become unmistakable."
],
"cfg": 3,
"recipe": "P06",
"strategy": "initial-physical-directing",
"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 Sadness. 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: {"fr": 56, "nl": 49, "en": 44, "de": 42, "es": 49}. 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 | 0.331 ± 0.028 | 6.166 ± 0.134 | 4.358 ± 0.195 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 20 | 0.336 ± 0.035 | 6.184 ± 0.128 | 4.340 ± 0.205 | 0.87% ± 2.13 |
| Rank32 × 0.75 | 20 | 0.337 ± 0.027 | 6.153 ± 0.171 | 4.299 ± 0.224 | 0.28% ± 1.24 |
| Rank32 × 1.0 | 20 | 0.324 ± 0.038 | 6.168 ± 0.132 | 4.237 ± 0.207 | 0.00% ± 0.00 |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.340 ± 0.040 | 6.263 ± 0.048 | 4.264 ± 0.085 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.309 ± 0.022 | 6.245 ± 0.094 | 4.216 ± 0.215 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.343 ± 0.029 | 6.332 ± 0.118 | 4.253 ± 0.243 | 1.39% ± 2.78 |
| Rank32 × 1.0 | 4 | 0.293 ± 0.007 | 6.271 ± 0.149 | 4.161 ± 0.324 | 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.362 · CE 6.21 · Genuine 4.21 · WER 0.0% | Target 0.299 · CE 6.25 · Genuine 4.11 · WER 0.0% | Target 0.304 · CE 6.31 · Genuine 3.96 · WER 5.6% | Target 0.283 · CE 6.24 · Genuine 3.94 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.374 · CE 6.32 · Genuine 4.17 · WER 0.0% | Target 0.310 · CE 6.11 · Genuine 3.97 · WER 0.0% | Target 0.364 · CE 6.18 · Genuine 4.17 · WER 0.0% | Target 0.294 · CE 6.08 · Genuine 3.84 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.343 · CE 6.25 · Genuine 4.36 · WER 0.0% | Target 0.340 · CE 6.31 · Genuine 4.37 · WER 0.0% | Target 0.336 · CE 6.38 · Genuine 4.38 · WER 0.0% | Target 0.299 · CE 6.42 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.283 · CE 6.28 · Genuine 4.31 · WER 0.0% | Target 0.288 · CE 6.31 · Genuine 4.42 · WER 0.0% | Target 0.367 · CE 6.46 · Genuine 4.51 · WER 0.0% | Target 0.298 · CE 6.35 · Genuine 4.52 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.312 ± 0.011 | 6.279 ± 0.122 | 4.471 ± 0.076 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.318 ± 0.030 | 6.326 ± 0.111 | 4.399 ± 0.163 | 2.88% ± 3.35 |
| Rank32 × 0.75 | 4 | 0.322 ± 0.030 | 6.295 ± 0.073 | 4.416 ± 0.223 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.323 ± 0.039 | 6.291 ± 0.092 | 4.339 ± 0.250 | 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.303 · CE 6.31 · Genuine 4.58 · WER 0.0% | Target 0.286 · CE 6.34 · Genuine 4.33 · WER 0.0% | Target 0.355 · CE 6.26 · Genuine 4.47 · WER 0.0% | Target 0.306 · CE 6.18 · Genuine 4.53 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.325 · CE 6.12 · Genuine 4.46 · WER 0.0% | Target 0.348 · CE 6.17 · Genuine 4.51 · WER 5.3% | Target 0.332 · CE 6.25 · Genuine 4.70 · WER 0.0% | Target 0.382 · CE 6.40 · Genuine 4.48 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 6.41 · Genuine 4.42 · WER 0.0% | Target 0.299 · CE 6.40 · Genuine 4.21 · WER 0.0% | Target 0.283 · CE 6.40 · Genuine 4.17 · WER 0.0% | Target 0.300 · CE 6.27 · Genuine 3.98 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.303 · CE 6.28 · Genuine 4.43 · WER 0.0% | Target 0.338 · CE 6.40 · Genuine 4.56 · WER 6.2% | Target 0.320 · CE 6.27 · Genuine 4.33 · WER 0.0% | Target 0.304 · CE 6.31 · Genuine 4.36 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.328 ± 0.022 | 6.164 ± 0.080 | 4.476 ± 0.078 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.362 ± 0.033 | 6.118 ± 0.093 | 4.379 ± 0.144 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.362 ± 0.027 | 6.070 ± 0.107 | 4.423 ± 0.107 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.372 ± 0.047 | 6.074 ± 0.111 | 4.299 ± 0.193 | 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.339 · CE 6.09 · Genuine 4.44 · WER 0.0% | Target 0.391 · CE 6.04 · Genuine 4.43 · WER 0.0% | Target 0.379 · CE 5.98 · Genuine 4.41 · WER 0.0% | Target 0.355 · CE 6.09 · Genuine 4.22 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.300 · CE 6.13 · Genuine 4.52 · WER 0.0% | Target 0.380 · CE 6.09 · Genuine 4.18 · WER 0.0% | Target 0.391 · CE 5.97 · Genuine 4.28 · WER 0.0% | Target 0.322 · CE 6.06 · Genuine 4.07 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.351 · CE 6.16 · Genuine 4.56 · WER 0.0% | Target 0.360 · CE 6.25 · Genuine 4.38 · WER 0.0% | Target 0.343 · CE 6.14 · Genuine 4.49 · WER 0.0% | Target 0.377 · CE 6.21 · Genuine 4.39 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.322 · CE 6.28 · Genuine 4.38 · WER 0.0% | Target 0.317 · CE 6.09 · Genuine 4.52 · WER 0.0% | Target 0.337 · CE 6.18 · Genuine 4.51 · WER 0.0% | Target 0.433 · CE 5.94 · Genuine 4.51 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.352 ± 0.013 | 6.124 ± 0.082 | 4.206 ± 0.120 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.349 ± 0.043 | 6.203 ± 0.057 | 4.286 ± 0.148 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.331 ± 0.018 | 5.971 ± 0.120 | 4.208 ± 0.157 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.328 ± 0.020 | 6.128 ± 0.047 | 4.195 ± 0.041 | 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.347 · CE 6.08 · Genuine 4.12 · WER 0.0% | Target 0.353 · CE 6.13 · Genuine 4.07 · WER 0.0% | Target 0.347 · CE 5.90 · Genuine 4.27 · WER 0.0% | Target 0.348 · CE 6.10 · Genuine 4.22 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.372 · CE 6.10 · Genuine 4.24 · WER 0.0% | Target 0.408 · CE 6.24 · Genuine 4.38 · WER 0.0% | Target 0.346 · CE 5.90 · Genuine 4.13 · WER 0.0% | Target 0.321 · CE 6.20 · Genuine 4.18 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.348 · CE 6.07 · Genuine 4.11 · WER 0.0% | Target 0.318 · CE 6.25 · Genuine 4.38 · WER 0.0% | Target 0.313 · CE 5.94 · Genuine 4.04 · WER 0.0% | Target 0.338 · CE 6.12 · Genuine 4.23 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. 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 Sadness. 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 Sadness. 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 0.342 · CE 6.25 · Genuine 4.36 · WER 0.0% | Target 0.318 · CE 6.20 · Genuine 4.32 · WER 0.0% | Target 0.319 · CE 6.15 · Genuine 4.39 · WER 0.0% | Target 0.303 · CE 6.09 · Genuine 4.14 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.322 ± 0.037 | 6.001 ± 0.121 | 4.374 ± 0.360 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.341 ± 0.028 | 6.029 ± 0.004 | 4.419 ± 0.332 | 1.47% ± 2.94 |
| Rank32 × 0.75 | 4 | 0.328 ± 0.020 | 6.098 ± 0.114 | 4.194 ± 0.324 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.303 ± 0.017 | 6.076 ± 0.073 | 4.192 ± 0.185 | 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Sadness. 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.309 · CE 5.87 · Genuine 3.96 · WER 0.0% | Target 0.321 · CE 6.03 · Genuine 3.96 · WER 0.0% | Target 0.356 · CE 6.11 · Genuine 4.16 · WER 0.0% | Target 0.299 · CE 5.98 · Genuine 4.01 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Sadness. 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.290 · CE 5.95 · Genuine 4.20 · WER 0.0% | Target 0.375 · CE 6.03 · Genuine 4.44 · WER 0.0% | Target 0.327 · CE 5.94 · Genuine 3.77 · WER 0.0% | Target 0.327 · CE 6.10 · Genuine 4.08 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Sadness. 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 Sadness. 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 0.315 · CE 6.16 · Genuine 4.61 · WER 0.0% | Target 0.352 · CE 6.02 · Genuine 4.73 · WER 5.9% | Target 0.318 · CE 6.20 · Genuine 4.53 · WER 0.0% | Target 0.287 · CE 6.16 · Genuine 4.27 · 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 Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Sadness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Sadness. 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 Sadness. 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 0.374 · CE 6.02 · Genuine 4.73 · WER 0.0% | Target 0.314 · CE 6.03 · Genuine 4.55 · WER 0.0% | Target 0.309 · CE 6.15 · Genuine 4.32 · WER 0.0% | Target 0.300 · CE 6.06 · Genuine 4.41 · WER 0.0% |