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 | 1.091 | 3.593 | 6.266 | 4.313 | 0.591 | 0.007 | 1.000 | pass |
| manual | 50 | 1.428 | 3.898 | 6.232 | 4.322 | 0.607 | 0.024 | 0.960 | pass |
| adapter | 50 | 1.427 | 3.896 | 6.202 | 4.270 | 0.593 | 0.029 | 0.940 | pass |
| matched_no_adapter | 50 | 1.428 | 3.898 | 6.232 | 4.322 | 0.607 | 0.024 | 0.960 | pass |
Incremental adapter gain versus same-CFG control: -0.002 z;95% cluster interval [-0.05828137696838877, 0.05234372776818093]. Versus best manual-only: -0.002 z. Manual-only versus standard: 0.337 z.
| Scale | CFG | Target z | CE | Genuine | WER | Provisional QA |
|---|---|---|---|---|---|---|
| 0.0 | 1.0 | 1.187 | 6.201 | 4.276 | 0.000 | True |
| 0.5 | 1.0 | 1.167 | 6.225 | 4.193 | 0.014 | True |
| 0.75 | 1.0 | 1.146 | 6.221 | 4.214 | 0.022 | True |
| 1.0 | 1.0 | 1.304 | 6.203 | 4.280 | 0.000 | True |
| 0.0 | 1.25 | 1.172 | 6.181 | 4.245 | 0.000 | True |
| 0.5 | 1.25 | 1.205 | 6.201 | 4.278 | 0.000 | False |
| 0.75 | 1.25 | 1.270 | 6.207 | 4.268 | 0.003 | True |
| 1.0 | 1.25 | 1.165 | 6.191 | 4.257 | 0.027 | True |
| 0.0 | 1.5 | 1.270 | 6.201 | 4.303 | 0.000 | True |
| 0.5 | 1.5 | 1.179 | 6.233 | 4.247 | 0.006 | True |
| 0.75 | 1.5 | 1.158 | 6.195 | 4.228 | 0.016 | True |
| 1.0 | 1.5 | 1.270 | 6.171 | 4.242 | 0.007 | True |
| 0.0 | 2.0 | 1.371 | 6.201 | 4.313 | 0.007 | True |
| 0.5 | 2.0 | 1.225 | 6.158 | 4.202 | 0.003 | True |
| 0.75 | 2.0 | 1.290 | 6.171 | 4.240 | 0.008 | True |
| 1.0 | 2.0 | 1.354 | 6.197 | 4.283 | 0.006 | True |
| 0.0 | 2.5 | 1.373 | 6.215 | 4.280 | 0.003 | True |
| 0.5 | 2.5 | 1.342 | 6.025 | 4.184 | 0.056 | True |
| 0.75 | 2.5 | 1.385 | 6.231 | 4.291 | 0.012 | True |
| 1.0 | 2.5 | 1.350 | 6.161 | 4.163 | 0.009 | True |
| 0.0 | 3.0 | 1.413 | 6.217 | 4.260 | 0.009 | True |
| 0.5 | 3.0 | 1.453 | 6.169 | 4.272 | 0.015 | True |
| 0.75 | 3.0 | 1.464 | 6.128 | 4.269 | 0.033 | True |
| 1.0 | 3.0 | 1.466 | 6.076 | 4.182 | 0.039 | True |
| 0.0 | 4.0 | 1.547 | 6.121 | 4.214 | 0.023 | True |
| 0.5 | 4.0 | 1.584 | 6.133 | 4.260 | 0.029 | True |
| 0.75 | 4.0 | 1.491 | 6.145 | 4.253 | 0.042 | True |
| 1.0 | 4.0 | 1.536 | 6.049 | 4.234 | 0.039 | True |
| 0.0 | 5.0 | 1.583 | 6.142 | 4.260 | 0.049 | True |
| 0.5 | 5.0 | 1.568 | 6.100 | 4.284 | 0.061 | False |
| 0.75 | 5.0 | 1.566 | 5.931 | 4.202 | 0.097 | False |
| 1.0 | 5.0 | 1.630 | 6.036 | 4.226 | 0.053 | True |
new_canonical_dimension_extension
{
"id": "canonical-extension-P05",
"general": "Very warm and personally engaged delivery, with kind resonance and a sympathetic interpersonal tone. Establish the delivery, sustain it through the middle thought and release it at the end.",
"inline": [
"Very warm and personally engaged delivery, with kind resonance and a sympathetic interpersonal tone. Establish the delivery, sustain it through the middle thought and release it at the end.",
"Very warm and personally engaged delivery, with kind resonance and a sympathetic interpersonal tone. Establish the delivery, sustain it through the middle thought and release it at the end.",
"Very warm and personally engaged delivery, with kind resonance and a sympathetic interpersonal tone. Establish the delivery, sustain it through the middle thought and release it at the end."
],
"recipe": "P05",
"cfg": 1.0,
"timing_syntax": "canonical",
"canonical_labels": true,
"lexical_proxy": false,
"origin": "new_canonical_manual_extension_requires_new_evidence"
}Exact machine-readable comparison · Agent tool recommendations
very warm vocal delivery. 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: {"es": 40, "nl": 30, "fr": 39, "de": 40, "en": 41}. 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 | 0.874 ± 0.048 | 6.199 ± 0.104 | 4.253 ± 0.236 | 0.61% ± 1.89 |
| Rank32 × 0.5 | 20 | 0.869 ± 0.043 | 6.210 ± 0.136 | 4.287 ± 0.218 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 20 | 0.884 ± 0.055 | 6.178 ± 0.155 | 4.297 ± 0.277 | 0.33% ± 1.49 |
| Rank32 × 1.0 | 20 | 0.879 ± 0.049 | 6.185 ± 0.102 | 4.256 ± 0.196 | 0.00% ± 0.00 |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.851 ± 0.035 | 6.255 ± 0.101 | 4.070 ± 0.338 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.848 ± 0.037 | 6.293 ± 0.072 | 4.226 ± 0.283 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.859 ± 0.076 | 6.253 ± 0.183 | 4.088 ± 0.269 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.864 ± 0.065 | 6.277 ± 0.026 | 4.297 ± 0.209 | 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.823 · CE 6.14 · Genuine 3.76 · WER 0.0% | Target 0.825 · CE 6.27 · Genuine 4.14 · WER 0.0% | Target 0.897 · CE 6.28 · Genuine 3.93 · WER 0.0% | Target 0.771 · CE 6.28 · Genuine 4.01 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.824 · CE 6.20 · Genuine 3.83 · WER 0.0% | Target 0.809 · CE 6.21 · Genuine 3.93 · WER 0.0% | Target 0.755 · CE 6.06 · Genuine 3.87 · WER 0.0% | Target 0.894 · CE 6.28 · Genuine 4.38 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.860 · CE 6.34 · Genuine 4.48 · WER 0.0% | Target 0.873 · CE 6.37 · Genuine 4.61 · WER 0.0% | Target 0.929 · CE 6.49 · Genuine 4.47 · WER 0.0% | Target 0.920 · CE 6.25 · Genuine 4.49 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.897 · CE 6.34 · Genuine 4.21 · WER 0.0% | Target 0.887 · CE 6.32 · Genuine 4.22 · WER 0.0% | Target 0.856 · CE 6.17 · Genuine 4.08 · WER 0.0% | Target 0.870 · CE 6.31 · Genuine 4.31 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.855 ± 0.033 | 6.334 ± 0.039 | 4.225 ± 0.124 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.846 ± 0.024 | 6.364 ± 0.080 | 4.256 ± 0.105 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.862 ± 0.022 | 6.283 ± 0.067 | 4.363 ± 0.151 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.842 ± 0.050 | 6.271 ± 0.059 | 4.269 ± 0.105 | 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.826 · CE 6.33 · Genuine 4.32 · WER 0.0% | Target 0.832 · CE 6.27 · Genuine 4.27 · WER 0.0% | Target 0.832 · CE 6.26 · Genuine 4.34 · WER 0.0% | Target 0.823 · CE 6.24 · Genuine 4.24 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.882 · CE 6.28 · Genuine 4.34 · WER 0.0% | Target 0.830 · CE 6.34 · Genuine 4.40 · WER 0.0% | Target 0.882 · CE 6.20 · Genuine 4.58 · WER 0.0% | Target 0.785 · CE 6.21 · Genuine 4.41 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. 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. (very warm vocal delivery. 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. (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.886 · CE 6.34 · Genuine 4.13 · WER 0.0% | Target 0.881 · CE 6.46 · Genuine 4.18 · WER 0.0% | Target 0.870 · CE 6.34 · Genuine 4.26 · WER 0.0% | Target 0.903 · CE 6.32 · Genuine 4.16 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. 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. (very warm vocal delivery. 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. (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.828 · CE 6.38 · Genuine 4.11 · WER 0.0% | Target 0.841 · CE 6.39 · Genuine 4.17 · WER 0.0% | Target 0.863 · CE 6.33 · Genuine 4.27 · WER 0.0% | Target 0.856 · CE 6.32 · Genuine 4.28 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.945 ± 0.023 | 6.187 ± 0.021 | 4.394 ± 0.174 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.915 ± 0.034 | 6.205 ± 0.086 | 4.443 ± 0.123 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.937 ± 0.013 | 6.227 ± 0.008 | 4.515 ± 0.275 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.922 ± 0.038 | 6.100 ± 0.059 | 4.154 ± 0.096 | 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.964 · CE 6.16 · Genuine 4.36 · WER 0.0% | Target 0.918 · CE 6.28 · Genuine 4.61 · WER 0.0% | Target 0.928 · CE 6.22 · Genuine 4.15 · WER 0.0% | Target 0.929 · CE 6.15 · Genuine 4.13 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.928 · CE 6.20 · Genuine 4.17 · WER 0.0% | Target 0.866 · CE 6.21 · Genuine 4.41 · WER 0.0% | Target 0.933 · CE 6.23 · Genuine 4.60 · WER 0.0% | Target 0.866 · CE 6.01 · Genuine 4.03 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. 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. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.965 · CE 6.21 · Genuine 4.57 · WER 0.0% | Target 0.931 · CE 6.25 · Genuine 4.31 · WER 0.0% | Target 0.956 · CE 6.22 · Genuine 4.51 · WER 0.0% | Target 0.942 · CE 6.11 · Genuine 4.21 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. 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. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.922 · CE 6.19 · Genuine 4.48 · WER 0.0% | Target 0.945 · CE 6.09 · Genuine 4.44 · WER 0.0% | Target 0.932 · CE 6.24 · Genuine 4.81 · WER 0.0% | Target 0.950 · CE 6.13 · Genuine 4.25 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.843 ± 0.039 | 6.116 ± 0.061 | 4.285 ± 0.118 | 1.39% ± 2.78 |
| Rank32 × 0.5 | 4 | 0.838 ± 0.038 | 6.132 ± 0.085 | 4.274 ± 0.045 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.846 ± 0.055 | 6.112 ± 0.102 | 4.388 ± 0.081 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.861 ± 0.031 | 6.172 ± 0.096 | 4.300 ± 0.038 | 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.837 · CE 6.06 · Genuine 4.23 · WER 0.0% | Target 0.824 · CE 6.21 · Genuine 4.30 · WER 0.0% | Target 0.878 · CE 5.96 · Genuine 4.37 · WER 0.0% | Target 0.863 · CE 6.17 · Genuine 4.34 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.793 · CE 6.08 · Genuine 4.29 · WER 0.0% | Target 0.802 · CE 6.06 · Genuine 4.22 · WER 0.0% | Target 0.804 · CE 6.16 · Genuine 4.51 · WER 0.0% | Target 0.832 · CE 6.11 · Genuine 4.26 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. 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. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.886 · CE 6.13 · Genuine 4.17 · WER 5.6% | Target 0.838 · CE 6.21 · Genuine 4.32 · WER 0.0% | Target 0.796 · CE 6.17 · Genuine 4.33 · WER 0.0% | Target 0.904 · CE 6.10 · Genuine 4.28 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. 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. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.856 · CE 6.20 · Genuine 4.44 · WER 0.0% | Target 0.890 · CE 6.05 · Genuine 4.26 · WER 0.0% | Target 0.907 · CE 6.17 · Genuine 4.34 · WER 0.0% | Target 0.845 · CE 6.31 · Genuine 4.32 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.878 ± 0.029 | 6.104 ± 0.047 | 4.294 ± 0.320 | 1.67% ± 3.33 |
| Rank32 × 0.5 | 4 | 0.895 ± 0.026 | 6.058 ± 0.106 | 4.236 ± 0.387 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.916 ± 0.040 | 6.014 ± 0.189 | 4.132 ± 0.367 | 1.67% ± 3.33 |
| Rank32 × 1.0 | 4 | 0.906 ± 0.017 | 6.108 ± 0.102 | 4.258 ± 0.397 | 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (very warm vocal delivery. 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. (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.890 · CE 6.07 · Genuine 4.11 · WER 0.0% | Target 0.878 · CE 5.95 · Genuine 4.04 · WER 0.0% | Target 0.858 · CE 5.80 · Genuine 3.95 · WER 0.0% | Target 0.897 · CE 6.08 · Genuine 3.89 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (very warm vocal delivery. 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. (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.838 · CE 6.17 · Genuine 4.01 · WER 6.7% | Target 0.870 · CE 6.11 · Genuine 3.79 · WER 0.0% | Target 0.922 · CE 5.95 · Genuine 3.74 · WER 6.7% | Target 0.891 · CE 6.01 · Genuine 3.94 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.878 · CE 6.09 · Genuine 4.32 · WER 0.0% | Target 0.904 · CE 6.18 · Genuine 4.53 · WER 0.0% | Target 0.937 · CE 6.25 · Genuine 4.58 · WER 0.0% | Target 0.908 · CE 6.09 · Genuine 4.60 · 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. very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (very warm vocal delivery. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (very warm vocal delivery. 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. (very warm vocal delivery. 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 0.905 · CE 6.08 · Genuine 4.73 · WER 0.0% | Target 0.928 · CE 5.99 · Genuine 4.58 · WER 0.0% | Target 0.946 · CE 6.06 · Genuine 4.26 · WER 0.0% | Target 0.929 · CE 6.25 · Genuine 4.61 · WER 0.0% |