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 2.0.
| Held-out condition | n | Target z↑ | Raw head | CE↑ | Genuine↑ | Voice↑ | WER↓ | Valid | QA |
|---|---|---|---|---|---|---|---|---|---|
| standard | 50 | -0.361 | 0.184 | 6.263 | 4.355 | 0.600 | 0.006 | 1.000 | pass |
| manual | 50 | 0.529 | 0.727 | 6.267 | 4.337 | 0.556 | 0.018 | 0.980 | pass |
| adapter | 50 | 0.313 | 0.596 | 6.291 | 4.354 | 0.560 | 0.008 | 1.000 | pass |
| matched_no_adapter | 50 | 0.263 | 0.565 | 6.274 | 4.385 | 0.529 | 0.011 | 1.000 | fail |
Incremental adapter gain versus same-CFG control: 0.050 z;95% cluster interval [-0.04686033974421556, 0.16163207751635264]. Versus best manual-only: -0.215 z. Manual-only versus standard: 0.889 z.
| Scale | CFG | Target z | CE | Genuine | WER | Provisional QA |
|---|---|---|---|---|---|---|
| 0.0 | 1.0 | 0.322 | 6.211 | 4.306 | 0.000 | False |
| 0.5 | 1.0 | 0.287 | 6.196 | 4.296 | 0.006 | False |
| 0.75 | 1.0 | 0.283 | 6.220 | 4.311 | 0.003 | False |
| 1.0 | 1.0 | 0.387 | 6.235 | 4.293 | 0.003 | False |
| 0.0 | 1.25 | 0.528 | 6.210 | 4.322 | 0.000 | False |
| 0.5 | 1.25 | 0.610 | 6.252 | 4.307 | 0.003 | False |
| 0.75 | 1.25 | 0.429 | 6.213 | 4.283 | 0.013 | True |
| 1.0 | 1.25 | 0.559 | 6.238 | 4.308 | 0.003 | True |
| 0.0 | 1.5 | 0.674 | 6.231 | 4.300 | 0.000 | False |
| 0.5 | 1.5 | 0.618 | 6.182 | 4.223 | 0.003 | True |
| 0.75 | 1.5 | 0.658 | 6.195 | 4.249 | 0.007 | False |
| 1.0 | 1.5 | 0.675 | 6.186 | 4.256 | 0.003 | False |
| 0.0 | 2.0 | 1.007 | 6.219 | 4.255 | 0.003 | True |
| 0.5 | 2.0 | 0.918 | 6.219 | 4.256 | 0.012 | False |
| 0.75 | 2.0 | 1.034 | 6.185 | 4.295 | 0.016 | False |
| 1.0 | 2.0 | 1.020 | 6.191 | 4.210 | 0.003 | False |
| 0.0 | 2.5 | 1.131 | 6.245 | 4.272 | 0.011 | False |
| 0.5 | 2.5 | 1.188 | 6.224 | 4.226 | 0.003 | False |
| 0.75 | 2.5 | 1.159 | 6.173 | 4.240 | 0.008 | False |
| 1.0 | 2.5 | 1.313 | 6.243 | 4.229 | 0.009 | False |
| 0.0 | 3.0 | 1.490 | 6.164 | 4.181 | 0.008 | False |
| 0.5 | 3.0 | 1.453 | 6.171 | 4.150 | 0.009 | False |
| 0.75 | 3.0 | 1.475 | 6.212 | 4.237 | 0.011 | False |
| 1.0 | 3.0 | 1.402 | 6.177 | 4.184 | 0.023 | False |
| 0.0 | 4.0 | 1.730 | 6.168 | 4.185 | 0.000 | False |
| 0.5 | 4.0 | 1.887 | 6.144 | 4.151 | 0.006 | False |
| 0.75 | 4.0 | 1.776 | 6.131 | 4.230 | 0.013 | False |
| 1.0 | 4.0 | 1.744 | 6.081 | 4.230 | 0.014 | False |
| 0.0 | 5.0 | 2.140 | 6.042 | 4.153 | 0.024 | False |
| 0.5 | 5.0 | 2.002 | 6.031 | 4.159 | 0.009 | False |
| 0.75 | 5.0 | 1.949 | 6.110 | 4.176 | 0.022 | False |
| 1.0 | 5.0 | 2.190 | 6.020 | 4.173 | 0.019 | False |
direct_manual_recipe
{
"id": "manual-1c5ef4ec2662",
"general": "Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.",
"inline": [
"Begin with a breathy intake that immediately suggests an upward rush of sensation.",
"Allow the mid-range of the voice to bloom with effortless, sustained resonance.",
"Let the final articulation dissolve into a warm, audible exhalation of pure delight."
],
"cfg": 3,
"recipe": "P04",
"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 Pleasure Ecstasy. 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: {"de": 4, "fr": 5, "en": 10, "nl": 7, "es": 4}. 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 | 0.486 ± 0.208 | 6.197 ± 0.137 | 4.365 ± 0.235 | 0.67% ± 2.05 |
| Rank32 × 0.5 | 20 | 0.438 ± 0.182 | 6.196 ± 0.127 | 4.335 ± 0.266 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 20 | 0.432 ± 0.191 | 6.232 ± 0.135 | 4.351 ± 0.182 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 20 | 0.423 ± 0.170 | 6.245 ± 0.124 | 4.334 ± 0.142 | 0.79% ± 3.53 |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.592 ± 0.257 | 6.257 ± 0.029 | 4.361 ± 0.220 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.571 ± 0.296 | 6.287 ± 0.138 | 4.234 ± 0.253 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.572 ± 0.311 | 6.342 ± 0.052 | 4.208 ± 0.176 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.554 ± 0.228 | 6.326 ± 0.071 | 4.297 ± 0.206 | 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.316 · CE 6.21 · Genuine 4.39 · WER 0.0% | Target 0.341 · CE 6.25 · Genuine 4.16 · WER 0.0% | Target 0.295 · CE 6.28 · Genuine 3.96 · WER 0.0% | Target 0.452 · CE 6.32 · Genuine 4.11 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.439 · CE 6.27 · Genuine 4.04 · WER 0.0% | Target 0.291 · CE 6.11 · Genuine 3.96 · WER 0.0% | Target 0.310 · CE 6.32 · Genuine 4.29 · WER 0.0% | Target 0.284 · CE 6.23 · Genuine 4.14 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.750 · CE 6.28 · Genuine 4.49 · WER 0.0% | Target 0.847 · CE 6.43 · Genuine 4.57 · WER 0.0% | Target 0.865 · CE 6.36 · Genuine 4.21 · WER 0.0% | Target 0.693 · CE 6.40 · Genuine 4.39 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.863 · CE 6.27 · Genuine 4.52 · WER 0.0% | Target 0.806 · CE 6.36 · Genuine 4.24 · WER 0.0% | Target 0.817 · CE 6.40 · Genuine 4.37 · WER 0.0% | Target 0.786 · CE 6.36 · Genuine 4.55 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.303 ± 0.047 | 6.249 ± 0.247 | 4.296 ± 0.291 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.308 ± 0.032 | 6.259 ± 0.139 | 4.383 ± 0.140 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.321 ± 0.053 | 6.358 ± 0.107 | 4.371 ± 0.086 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.377 ± 0.139 | 6.386 ± 0.123 | 4.419 ± 0.098 | 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.263 · CE 6.27 · Genuine 4.43 · WER 0.0% | Target 0.278 · CE 6.23 · Genuine 4.44 · WER 0.0% | Target 0.267 · CE 6.26 · Genuine 4.38 · WER 0.0% | Target 0.261 · CE 6.38 · Genuine 4.49 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.267 · CE 5.90 · Genuine 4.22 · WER 0.0% | Target 0.286 · CE 6.09 · Genuine 4.44 · WER 0.0% | Target 0.299 · CE 6.28 · Genuine 4.48 · WER 0.0% | Target 0.258 · CE 6.22 · Genuine 4.51 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 6.34 · Genuine 3.93 · WER 0.0% | Target 0.322 · CE 6.30 · Genuine 4.17 · WER 0.0% | Target 0.392 · CE 6.41 · Genuine 4.34 · WER 0.0% | Target 0.455 · CE 6.43 · Genuine 4.37 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.364 · CE 6.48 · Genuine 4.61 · WER 0.0% | Target 0.345 · CE 6.42 · Genuine 4.47 · WER 0.0% | Target 0.325 · CE 6.48 · Genuine 4.28 · WER 0.0% | Target 0.532 · CE 6.52 · Genuine 4.31 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.539 ± 0.186 | 6.174 ± 0.064 | 4.614 ± 0.065 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.542 ± 0.128 | 6.209 ± 0.145 | 4.539 ± 0.187 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.520 ± 0.186 | 6.207 ± 0.105 | 4.528 ± 0.163 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.452 ± 0.161 | 6.187 ± 0.120 | 4.349 ± 0.092 | 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.374 · CE 6.10 · Genuine 4.63 · WER 0.0% | Target 0.418 · CE 6.00 · Genuine 4.52 · WER 0.0% | Target 0.311 · CE 6.09 · Genuine 4.38 · WER 0.0% | Target 0.318 · CE 6.07 · Genuine 4.41 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.390 · CE 6.14 · Genuine 4.55 · WER 0.0% | Target 0.468 · CE 6.30 · Genuine 4.66 · WER 0.0% | Target 0.763 · CE 6.20 · Genuine 4.48 · WER 0.0% | Target 0.315 · CE 6.11 · Genuine 4.29 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.748 · CE 6.21 · Genuine 4.70 · WER 0.0% | Target 0.708 · CE 6.23 · Genuine 4.70 · WER 0.0% | Target 0.524 · CE 6.35 · Genuine 4.49 · WER 0.0% | Target 0.634 · CE 6.24 · Genuine 4.44 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.645 · CE 6.25 · Genuine 4.58 · WER 0.0% | Target 0.573 · CE 6.31 · Genuine 4.28 · WER 0.0% | Target 0.484 · CE 6.19 · Genuine 4.76 · WER 0.0% | Target 0.541 · CE 6.33 · Genuine 4.25 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.308 ± 0.061 | 6.150 ± 0.036 | 4.272 ± 0.104 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.277 ± 0.020 | 6.122 ± 0.069 | 4.203 ± 0.097 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.279 ± 0.005 | 6.154 ± 0.107 | 4.302 ± 0.089 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.280 ± 0.008 | 6.152 ± 0.065 | 4.214 ± 0.098 | 3.95% ± 7.89 |
| 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.306 · CE 6.20 · Genuine 4.17 · WER 0.0% | Target 0.250 · CE 6.09 · Genuine 4.12 · WER 0.0% | Target 0.272 · CE 6.25 · Genuine 4.40 · WER 0.0% | Target 0.280 · CE 6.16 · Genuine 4.21 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.261 · CE 6.13 · Genuine 4.29 · WER 0.0% | Target 0.278 · CE 6.06 · Genuine 4.12 · WER 0.0% | Target 0.279 · CE 6.00 · Genuine 4.33 · WER 0.0% | Target 0.269 · CE 6.07 · Genuine 4.35 · WER 15.8% |
| 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.394 · CE 6.12 · Genuine 4.22 · WER 0.0% | Target 0.282 · CE 6.22 · Genuine 4.31 · WER 0.0% | Target 0.284 · CE 6.20 · Genuine 4.29 · WER 0.0% | Target 0.284 · CE 6.15 · Genuine 4.12 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.270 · CE 6.16 · Genuine 4.41 · WER 0.0% | Target 0.298 · CE 6.11 · Genuine 4.26 · WER 0.0% | Target 0.279 · CE 6.17 · Genuine 4.19 · WER 0.0% | Target 0.288 · CE 6.23 · Genuine 4.18 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.687 ± 0.079 | 6.158 ± 0.194 | 4.280 ± 0.304 | 3.33% ± 3.85 |
| Rank32 × 0.5 | 4 | 0.494 ± 0.074 | 6.104 ± 0.058 | 4.317 ± 0.474 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.468 ± 0.101 | 6.100 ± 0.091 | 4.347 ± 0.252 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.452 ± 0.174 | 6.174 ± 0.029 | 4.388 ± 0.151 | 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.655 · CE 6.17 · Genuine 3.96 · WER 6.7% | Target 0.564 · CE 6.09 · Genuine 3.91 · WER 0.0% | Target 0.548 · CE 6.16 · Genuine 4.34 · WER 0.0% | Target 0.506 · CE 6.14 · Genuine 4.22 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.803 · CE 5.88 · Genuine 4.11 · WER 6.7% | Target 0.412 · CE 6.06 · Genuine 3.90 · WER 0.0% | Target 0.328 · CE 5.97 · Genuine 3.99 · WER 0.0% | Target 0.270 · CE 6.21 · Genuine 4.31 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.668 · CE 6.31 · Genuine 4.63 · WER 0.0% | Target 0.549 · CE 6.19 · Genuine 4.76 · WER 0.0% | Target 0.537 · CE 6.16 · Genuine 4.55 · WER 0.0% | Target 0.364 · CE 6.16 · Genuine 4.48 · 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 0.623 · CE 6.27 · Genuine 4.42 · WER 0.0% | Target 0.449 · CE 6.08 · Genuine 4.70 · WER 0.0% | Target 0.458 · CE 6.12 · Genuine 4.51 · WER 0.0% | Target 0.669 · CE 6.19 · Genuine 4.55 · WER 0.0% |