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 | 1.556 | 2.828 | 6.250 | 4.314 | 0.582 | 0.009 | 1.000 | pass |
| manual | 50 | 2.309 | 3.610 | 6.273 | 4.107 | 0.547 | 0.005 | 1.000 | pass |
| adapter | 50 | 2.388 | 3.692 | 6.257 | 4.084 | 0.550 | 0.002 | 1.000 | pass |
| matched_no_adapter | 50 | 2.309 | 3.610 | 6.273 | 4.107 | 0.547 | 0.005 | 1.000 | pass |
Incremental adapter gain versus same-CFG control: 0.079 z;95% cluster interval [-0.017187450263823296, 0.19531244847088255]. Versus best manual-only: 0.079 z. Manual-only versus standard: 0.753 z.
| Scale | CFG | Target z | CE | Genuine | WER | Provisional QA |
|---|---|---|---|---|---|---|
| 0.0 | 1.0 | 1.632 | 6.214 | 4.333 | 0.003 | True |
| 0.5 | 1.0 | 1.721 | 6.221 | 4.292 | 0.003 | True |
| 0.75 | 1.0 | 1.729 | 6.222 | 4.317 | 0.000 | True |
| 1.0 | 1.0 | 1.754 | 6.174 | 4.249 | 0.000 | True |
| 0.0 | 1.25 | 1.693 | 6.203 | 4.324 | 0.029 | True |
| 0.5 | 1.25 | 1.675 | 6.201 | 4.268 | 0.000 | True |
| 0.75 | 1.25 | 1.783 | 6.184 | 4.251 | 0.000 | True |
| 1.0 | 1.25 | 1.889 | 6.193 | 4.167 | 0.022 | True |
| 0.0 | 1.5 | 1.704 | 6.224 | 4.337 | 0.000 | True |
| 0.5 | 1.5 | 1.879 | 6.200 | 4.278 | 0.000 | True |
| 0.75 | 1.5 | 1.816 | 6.178 | 4.221 | 0.006 | True |
| 1.0 | 1.5 | 2.009 | 6.176 | 4.159 | 0.000 | True |
| 0.0 | 2.0 | 1.740 | 6.207 | 4.277 | 0.000 | True |
| 0.5 | 2.0 | 1.796 | 6.189 | 4.282 | 0.000 | True |
| 0.75 | 2.0 | 1.962 | 6.166 | 4.222 | 0.000 | True |
| 1.0 | 2.0 | 2.050 | 6.228 | 4.221 | 0.000 | True |
| 0.0 | 2.5 | 1.843 | 6.170 | 4.273 | 0.000 | True |
| 0.5 | 2.5 | 1.925 | 6.161 | 4.219 | 0.000 | True |
| 0.75 | 2.5 | 1.989 | 6.202 | 4.179 | 0.000 | True |
| 1.0 | 2.5 | 2.035 | 6.175 | 4.130 | 0.003 | True |
| 0.0 | 3.0 | 1.864 | 6.193 | 4.258 | 0.000 | True |
| 0.5 | 3.0 | 1.929 | 6.230 | 4.273 | 0.011 | True |
| 0.75 | 3.0 | 2.121 | 6.150 | 4.151 | 0.000 | True |
| 1.0 | 3.0 | 2.083 | 6.175 | 4.206 | 0.000 | True |
| 0.0 | 4.0 | 2.053 | 6.150 | 4.147 | 0.011 | True |
| 0.5 | 4.0 | 2.128 | 6.165 | 4.161 | 0.003 | True |
| 0.75 | 4.0 | 2.069 | 6.149 | 4.203 | 0.006 | True |
| 1.0 | 4.0 | 2.240 | 6.204 | 4.179 | 0.024 | True |
| 0.0 | 5.0 | 2.150 | 6.178 | 4.209 | 0.013 | True |
| 0.5 | 5.0 | 2.272 | 6.155 | 4.172 | 0.034 | True |
| 0.75 | 5.0 | 2.282 | 6.201 | 4.152 | 0.000 | False |
| 1.0 | 5.0 | 2.204 | 6.111 | 4.132 | 0.032 | True |
direct_manual_recipe
{
"id": "manual-553924db97fc",
"general": "Calm, unmistakable authority; grounded resonance, firm attacks and decisive sentence endings. Establish it immediately. Calm, unmistakable authority; grounded resonance, firm attacks and decisive sentence endings. Sustain the delivery. Calm, unmistakable authority; grounded resonance, firm attacks and decisive sentence endings. Preserve the intended style through the end. Let the local direction carry the intended delivery beside each sentence.",
"inline": [
"Calm, unmistakable authority; grounded resonance, firm attacks and decisive sentence endings. Establish it immediately. Let the local direction carry the intended delivery beside each sentence.",
"Calm, unmistakable authority; grounded resonance, firm attacks and decisive sentence endings. Sustain the delivery. Let the local direction carry the intended delivery beside each sentence.",
"Calm, unmistakable authority; grounded resonance, firm attacks and decisive sentence endings. Preserve the intended style through the end. Let the local direction carry the intended delivery beside each sentence."
],
"cfg": 3,
"recipe": "P09",
"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
Strong Authoritative Style. 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": 47, "es": 37, "nl": 44, "de": 40, "en": 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 | 0.894 ± 0.067 | 6.176 ± 0.166 | 4.376 ± 0.205 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 20 | 0.915 ± 0.084 | 6.183 ± 0.133 | 4.312 ± 0.169 | 0.53% ± 2.35 |
| Rank32 × 0.75 | 20 | 0.900 ± 0.099 | 6.178 ± 0.200 | 4.303 ± 0.295 | 0.79% ± 3.53 |
| Rank32 × 1.0 | 20 | 0.931 ± 0.062 | 6.186 ± 0.106 | 4.280 ± 0.138 | 0.61% ± 1.89 |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.848 ± 0.104 | 6.299 ± 0.095 | 4.339 ± 0.163 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.810 ± 0.118 | 6.261 ± 0.023 | 4.259 ± 0.230 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.863 ± 0.154 | 6.318 ± 0.119 | 4.044 ± 0.322 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.856 ± 0.095 | 6.251 ± 0.062 | 4.139 ± 0.138 | 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.879 · CE 6.21 · Genuine 4.24 · WER 0.0% | Target 0.969 · CE 6.24 · Genuine 3.92 · WER 0.0% | Target 0.967 · CE 6.19 · Genuine 3.73 · WER 0.0% | Target 0.870 · CE 6.25 · Genuine 4.14 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.974 · CE 6.23 · Genuine 4.16 · WER 0.0% | Target 0.829 · CE 6.25 · Genuine 4.36 · WER 0.0% | Target 0.984 · CE 6.25 · Genuine 3.82 · WER 0.0% | Target 0.979 · CE 6.17 · Genuine 3.94 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.730 · CE 6.36 · Genuine 4.51 · WER 0.0% | Target 0.710 · CE 6.29 · Genuine 4.34 · WER 0.0% | Target 0.847 · CE 6.43 · Genuine 4.24 · WER 0.0% | Target 0.754 · CE 6.25 · Genuine 4.24 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.810 · CE 6.40 · Genuine 4.44 · WER 0.0% | Target 0.731 · CE 6.26 · Genuine 4.42 · WER 0.0% | Target 0.651 · CE 6.41 · Genuine 4.39 · WER 0.0% | Target 0.821 · CE 6.32 · Genuine 4.22 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.941 ± 0.028 | 6.293 ± 0.107 | 4.430 ± 0.163 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.969 ± 0.020 | 6.318 ± 0.124 | 4.303 ± 0.162 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.964 ± 0.026 | 6.287 ± 0.128 | 4.253 ± 0.183 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.975 ± 0.011 | 6.291 ± 0.129 | 4.333 ± 0.093 | 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.928 · CE 6.14 · Genuine 4.47 · WER 0.0% | Target 0.948 · CE 6.32 · Genuine 4.55 · WER 0.0% | Target 0.984 · CE 6.13 · Genuine 4.12 · WER 0.0% | Target 0.976 · CE 6.25 · Genuine 4.34 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.971 · CE 6.29 · Genuine 4.47 · WER 0.0% | Target 0.984 · CE 6.14 · Genuine 4.22 · WER 0.0% | Target 0.945 · CE 6.23 · Genuine 4.46 · WER 0.0% | Target 0.984 · CE 6.13 · Genuine 4.33 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. 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. (Strong Authoritative Style. 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. (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.958 · CE 6.36 · Genuine 4.20 · WER 0.0% | Target 0.986 · CE 6.40 · Genuine 4.20 · WER 0.0% | Target 0.989 · CE 6.40 · Genuine 4.08 · WER 0.0% | Target 0.980 · CE 6.36 · Genuine 4.22 · WER 0.0% |
| Seed 1702 Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Exact GENERAL / SCRIPT promptGENERAL: One adult speaker in a clean recording. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. 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. (Strong Authoritative Style. 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. (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen. | Target 0.908 · CE 6.37 · Genuine 4.58 · WER 0.0% | Target 0.956 · CE 6.41 · Genuine 4.24 · WER 0.0% | Target 0.938 · CE 6.39 · Genuine 4.36 · WER 0.0% | Target 0.960 · CE 6.43 · Genuine 4.44 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.886 ± 0.053 | 6.154 ± 0.062 | 4.457 ± 0.193 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.894 ± 0.062 | 6.092 ± 0.108 | 4.438 ± 0.179 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.817 ± 0.086 | 6.136 ± 0.139 | 4.567 ± 0.154 | 3.95% ± 7.89 |
| Rank32 × 1.0 | 4 | 0.938 ± 0.011 | 6.132 ± 0.102 | 4.372 ± 0.073 | 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.863 · CE 6.11 · Genuine 4.24 · WER 0.0% | Target 0.904 · CE 6.02 · Genuine 4.33 · WER 0.0% | Target 0.780 · CE 6.31 · Genuine 4.57 · WER 0.0% | Target 0.941 · CE 6.03 · Genuine 4.33 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.936 · CE 6.25 · Genuine 4.56 · WER 0.0% | Target 0.920 · CE 6.05 · Genuine 4.48 · WER 0.0% | Target 0.946 · CE 6.18 · Genuine 4.44 · WER 0.0% | Target 0.945 · CE 6.14 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. 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. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.822 · CE 6.13 · Genuine 4.67 · WER 0.0% | Target 0.946 · CE 6.25 · Genuine 4.27 · WER 0.0% | Target 0.776 · CE 5.99 · Genuine 4.47 · WER 15.8% | Target 0.945 · CE 6.27 · Genuine 4.41 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. 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. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.921 · CE 6.13 · Genuine 4.36 · WER 0.0% | Target 0.805 · CE 6.04 · Genuine 4.67 · WER 0.0% | Target 0.767 · CE 6.06 · Genuine 4.78 · WER 0.0% | Target 0.922 · CE 6.09 · Genuine 4.46 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.908 ± 0.070 | 6.187 ± 0.096 | 4.285 ± 0.083 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.972 ± 0.019 | 6.132 ± 0.036 | 4.303 ± 0.065 | 2.63% ± 5.26 |
| Rank32 × 0.75 | 4 | 0.973 ± 0.025 | 6.130 ± 0.025 | 4.239 ± 0.150 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.945 ± 0.058 | 6.150 ± 0.044 | 4.310 ± 0.151 | 1.39% ± 2.78 |
| 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.849 · CE 6.10 · Genuine 4.21 · WER 0.0% | Target 0.980 · CE 6.13 · Genuine 4.34 · WER 0.0% | Target 0.990 · CE 6.10 · Genuine 4.04 · WER 0.0% | Target 0.929 · CE 6.11 · Genuine 4.42 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.845 · CE 6.11 · Genuine 4.36 · WER 0.0% | Target 0.976 · CE 6.13 · Genuine 4.33 · WER 10.5% | Target 0.994 · CE 6.12 · Genuine 4.24 · WER 0.0% | Target 0.871 · CE 6.13 · Genuine 4.32 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. 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. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.964 · CE 6.25 · Genuine 4.22 · WER 0.0% | Target 0.945 · CE 6.17 · Genuine 4.33 · WER 0.0% | Target 0.967 · CE 6.14 · Genuine 4.27 · WER 0.0% | Target 0.998 · CE 6.21 · Genuine 4.09 · WER 5.6% |
| 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. 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. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.973 · CE 6.29 · Genuine 4.36 · WER 0.0% | Target 0.988 · CE 6.09 · Genuine 4.21 · WER 0.0% | Target 0.941 · CE 6.16 · Genuine 4.41 · WER 0.0% | Target 0.983 · CE 6.14 · Genuine 4.41 · WER 0.0% |
Fixed speaker reference:
| Condition | n | Target score ↑ | Content Enjoyment ↑ | Genuineness ↑ | WER ↓ |
|---|---|---|---|---|---|
| Merged base, no bucket adapter | 4 | 0.890 ± 0.055 | 5.946 ± 0.176 | 4.369 ± 0.377 | 0.00% ± 0.00 |
| Rank32 × 0.5 | 4 | 0.929 ± 0.044 | 6.112 ± 0.173 | 4.255 ± 0.191 | 0.00% ± 0.00 |
| Rank32 × 0.75 | 4 | 0.885 ± 0.075 | 6.020 ± 0.349 | 4.410 ± 0.403 | 0.00% ± 0.00 |
| Rank32 × 1.0 | 4 | 0.941 ± 0.036 | 6.106 ± 0.060 | 4.245 ± 0.140 | 1.67% ± 3.33 |
| 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Strong Authoritative Style. 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. (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.910 · CE 5.69 · Genuine 4.26 · WER 0.0% | Target 0.972 · CE 6.24 · Genuine 4.17 · WER 0.0% | Target 0.972 · CE 5.94 · Genuine 4.24 · WER 0.0% | Target 0.980 · CE 6.16 · Genuine 4.28 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta. (Strong Authoritative Style. 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. (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo. | Target 0.955 · CE 5.96 · Genuine 3.90 · WER 0.0% | Target 0.925 · CE 5.86 · Genuine 4.06 · WER 0.0% | Target 0.922 · CE 5.56 · Genuine 3.92 · WER 0.0% | Target 0.896 · CE 6.02 · Genuine 4.18 · WER 6.7% |
| 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.830 · CE 6.06 · Genuine 4.78 · WER 0.0% | Target 0.950 · CE 6.13 · Genuine 4.28 · WER 0.0% | Target 0.833 · CE 6.32 · Genuine 4.73 · WER 0.0% | Target 0.957 · CE 6.14 · Genuine 4.43 · 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. Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word. SCRIPT: (Strong Authoritative Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita. (Strong Authoritative Style. 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. (Strong Authoritative Style. 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 0.863 · CE 6.07 · Genuine 4.53 · WER 0.0% | Target 0.870 · CE 6.22 · Genuine 4.51 · WER 0.0% | Target 0.811 · CE 6.25 · Genuine 4.75 · WER 0.0% | Target 0.930 · CE 6.10 · Genuine 4.10 · WER 0.0% |