Intense Sourness · rank32 comparison

Humaneness Voice Large 1.5 and 1.6 Alpha — model and manual navigation

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.

Standard vs manual prompts: matched LoRA / CFG comparison

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 1.25.

Held-out conditionnTarget z↑Raw headCE↑Genuine↑Voice↑WER↓ValidQA
standard50-0.2900.0906.2424.3780.6030.0120.980pass
manual50-0.2860.0916.2364.2960.5840.0111.000pass
adapter500.0650.2436.1754.2090.5610.0081.000pass
matched_no_adapter50-0.0120.2106.1984.2250.5330.0081.000fail

Incremental adapter gain versus same-CFG control: 0.076 z;95% cluster interval [0.01593749149162768, 0.15835937627625585]. Versus best manual-only: 0.351 z. Manual-only versus standard: 0.004 z.

All32development CFG × strength cells
ScaleCFGTarget zCEGenuineWERProvisional QA
0.01.0-0.3606.1854.3040.003False
0.51.0-0.3686.1504.3100.000True
0.751.0-0.3346.1494.3780.006True
1.01.0-0.3536.1614.2960.006True
0.01.25-0.2936.1814.3320.000True
0.51.25-0.3306.1904.2940.000True
0.751.25-0.3556.1744.2980.000False
1.01.25-0.2976.1664.2960.000True
0.01.5-0.3466.1384.2960.003False
0.51.5-0.3156.1144.2470.003False
0.751.5-0.2766.1194.3030.000True
1.01.5-0.2266.1724.3170.006False
0.02.0-0.2896.1014.2700.000False
0.52.0-0.1576.1164.2170.006False
0.752.0-0.1746.0654.2190.006False
1.02.0-0.2816.1274.2460.000True
0.02.5-0.2636.1074.2830.003False
0.52.5-0.1756.0724.2160.000True
0.752.5-0.1226.0654.2150.008False
1.02.5-0.2476.0584.2230.003False
0.03.0-0.0195.9834.1290.009False
0.53.00.1875.9744.1050.000False
0.753.00.1846.0574.1460.003False
1.03.00.1475.9854.1410.005False
0.04.00.4475.8603.9370.003False
0.54.00.6375.9154.0240.000False
0.754.00.2985.9734.1200.006False
1.04.00.7805.8823.9140.008False
0.05.00.7405.7963.9150.005False
0.55.01.1635.7103.8670.006False
0.755.01.0465.7463.8060.006False
1.05.00.9125.7073.7640.012False
Selected English acting directions and their provenance

direct_manual_recipe

{
  "id": "manual-909f760b761b",
  "general": "Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.",
  "inline": [
    "Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.",
    "Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.",
    "Finish the utterance with a sudden, abrupt cessation of vocal energy."
  ],
  "cfg": 3,
  "recipe": "P05",
  "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

What is compared?

Intense Sourness. Base: 1.5 Alpha + merged real-speech rank4; new adapter: rank32. Every row is a matched seed/text/reference test. Scale zero disables the new adapter; all other scales are applied absolutely, never compounded.

Adapter training data: {"en": 38, "es": 15, "fr": 12, "de": 25, "nl": 6}. 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.

ConditionnTarget score ↑Content Enjoyment ↑Genuineness ↑WER ↓
Merged base, no bucket adapter200.359 ± 0.0526.160 ± 0.1384.405 ± 0.1930.28% ± 1.24
Rank32 × 0.5200.370 ± 0.0536.166 ± 0.1104.385 ± 0.1910.54% ± 1.67
Rank32 × 0.75200.380 ± 0.0526.159 ± 0.1354.418 ± 0.2530.28% ± 1.24
Rank32 × 1.0200.381 ± 0.1126.179 ± 0.1204.344 ± 0.1890.00% ± 0.00

English

Fixed speaker reference:

ConditionnTarget score ↑Content Enjoyment ↑Genuineness ↑WER ↓
Merged base, no bucket adapter40.342 ± 0.0426.251 ± 0.0944.195 ± 0.2110.00% ± 0.00
Rank32 × 0.540.352 ± 0.0486.271 ± 0.1194.222 ± 0.2020.00% ± 0.00
Rank32 × 0.7540.356 ± 0.0516.251 ± 0.1324.263 ± 0.2780.00% ± 0.00
Rank32 × 1.040.331 ± 0.0636.303 ± 0.0854.208 ± 0.2040.00% ± 0.00
Prompt / seedMerged base · no new LoRARank32 × 0.5Rank32 × 0.75Rank32 × 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.383 · CE 6.34 · Genuine 4.18 · WER 0.0%

Target 0.385 · CE 6.25 · Genuine 4.18 · WER 0.0%

Target 0.380 · CE 6.14 · Genuine 3.98 · WER 0.0%

Target 0.383 · CE 6.24 · Genuine 3.99 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.370 · CE 6.13 · Genuine 3.93 · WER 0.0%

Target 0.400 · CE 6.11 · Genuine 3.98 · WER 0.0%

Target 0.415 · CE 6.17 · Genuine 4.11 · WER 0.0%

Target 0.388 · CE 6.22 · Genuine 4.16 · WER 0.0%

Seed 1701

I found the little box. It was beside the old window. We can look inside together.

Exact GENERAL / SCRIPT prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.322 · CE 6.24 · Genuine 4.22 · WER 0.0%

Target 0.298 · CE 6.37 · Genuine 4.26 · WER 0.0%

Target 0.321 · CE 6.25 · Genuine 4.36 · WER 0.0%

Target 0.280 · CE 6.37 · Genuine 4.20 · WER 0.0%

Seed 1702

I found the little box. It was beside the old window. We can look inside together.

Exact GENERAL / SCRIPT prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.292 · CE 6.30 · Genuine 4.44 · WER 0.0%

Target 0.327 · CE 6.35 · Genuine 4.47 · WER 0.0%

Target 0.306 · CE 6.44 · Genuine 4.61 · WER 0.0%

Target 0.272 · CE 6.38 · Genuine 4.48 · WER 0.0%

German

Fixed speaker reference:

ConditionnTarget score ↑Content Enjoyment ↑Genuineness ↑WER ↓
Merged base, no bucket adapter40.356 ± 0.0416.235 ± 0.1424.388 ± 0.1000.00% ± 0.00
Rank32 × 0.540.351 ± 0.0566.251 ± 0.1084.308 ± 0.1370.00% ± 0.00
Rank32 × 0.7540.377 ± 0.0476.217 ± 0.1124.515 ± 0.1800.00% ± 0.00
Rank32 × 1.040.378 ± 0.0746.289 ± 0.0754.521 ± 0.1450.00% ± 0.00
Prompt / seedMerged base · no new LoRARank32 × 0.5Rank32 × 0.75Rank32 × 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.396 · CE 6.30 · Genuine 4.53 · WER 0.0%

Target 0.404 · CE 6.17 · Genuine 4.34 · WER 0.0%

Target 0.431 · CE 6.09 · Genuine 4.63 · WER 0.0%

Target 0.462 · CE 6.25 · Genuine 4.67 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.386 · CE 6.02 · Genuine 4.37 · WER 0.0%

Target 0.377 · CE 6.16 · Genuine 4.11 · WER 0.0%

Target 0.401 · CE 6.15 · Genuine 4.62 · WER 0.0%

Target 0.407 · CE 6.21 · Genuine 4.62 · WER 0.0%

Seed 1701

Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.

Exact GENERAL / SCRIPT prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.

Target 0.325 · CE 6.32 · Genuine 4.31 · WER 0.0%

Target 0.275 · CE 6.38 · Genuine 4.34 · WER 0.0%

Target 0.327 · CE 6.31 · Genuine 4.25 · WER 0.0%

Target 0.290 · CE 6.36 · Genuine 4.39 · WER 0.0%

Seed 1702

Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.

Exact GENERAL / SCRIPT prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.

Target 0.318 · CE 6.29 · Genuine 4.34 · WER 0.0%

Target 0.349 · CE 6.30 · Genuine 4.43 · WER 0.0%

Target 0.350 · CE 6.32 · Genuine 4.56 · WER 0.0%

Target 0.352 · CE 6.35 · Genuine 4.40 · WER 0.0%

French

Fixed speaker reference:

ConditionnTarget score ↑Content Enjoyment ↑Genuineness ↑WER ↓
Merged base, no bucket adapter40.327 ± 0.0406.148 ± 0.1284.556 ± 0.1220.00% ± 0.00
Rank32 × 0.540.337 ± 0.0506.140 ± 0.0404.570 ± 0.0881.39% ± 2.78
Rank32 × 0.7540.350 ± 0.0336.187 ± 0.0634.686 ± 0.0680.00% ± 0.00
Rank32 × 1.040.333 ± 0.0226.122 ± 0.0744.380 ± 0.1750.00% ± 0.00
Prompt / seedMerged base · no new LoRARank32 × 0.5Rank32 × 0.75Rank32 × 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.365 · CE 6.06 · Genuine 4.43 · WER 0.0%

Target 0.311 · CE 6.17 · Genuine 4.63 · WER 5.6%

Target 0.358 · CE 6.19 · Genuine 4.63 · WER 0.0%

Target 0.354 · CE 6.01 · Genuine 4.16 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.346 · CE 6.27 · Genuine 4.63 · WER 0.0%

Target 0.412 · CE 6.12 · Genuine 4.65 · WER 0.0%

Target 0.393 · CE 6.10 · Genuine 4.68 · WER 0.0%

Target 0.317 · CE 6.17 · Genuine 4.39 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.325 · CE 6.01 · Genuine 4.68 · WER 0.0%

Target 0.314 · CE 6.09 · Genuine 4.55 · WER 0.0%

Target 0.331 · CE 6.25 · Genuine 4.78 · WER 0.0%

Target 0.349 · CE 6.13 · Genuine 4.58 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.271 · CE 6.25 · Genuine 4.48 · WER 0.0%

Target 0.309 · CE 6.17 · Genuine 4.46 · WER 0.0%

Target 0.318 · CE 6.21 · Genuine 4.65 · WER 0.0%

Target 0.311 · CE 6.17 · Genuine 4.39 · WER 0.0%

Dutch

Fixed speaker reference:

ConditionnTarget score ↑Content Enjoyment ↑Genuineness ↑WER ↓
Merged base, no bucket adapter40.425 ± 0.0196.104 ± 0.0844.452 ± 0.0531.39% ± 2.78
Rank32 × 0.540.433 ± 0.0396.116 ± 0.0644.313 ± 0.1591.32% ± 2.63
Rank32 × 0.7540.440 ± 0.0516.072 ± 0.1144.230 ± 0.0911.39% ± 2.78
Rank32 × 1.040.531 ± 0.1686.080 ± 0.0474.261 ± 0.1110.00% ± 0.00
Prompt / seedMerged base · no new LoRARank32 × 0.5Rank32 × 0.75Rank32 × 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.449 · CE 6.17 · Genuine 4.41 · WER 0.0%

Target 0.489 · CE 6.14 · Genuine 4.16 · WER 5.3%

Target 0.502 · CE 5.99 · Genuine 4.27 · WER 0.0%

Target 0.782 · CE 6.06 · Genuine 4.17 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.431 · CE 6.01 · Genuine 4.41 · WER 0.0%

Target 0.426 · CE 6.18 · Genuine 4.48 · WER 0.0%

Target 0.463 · CE 6.15 · Genuine 4.31 · WER 0.0%

Target 0.474 · CE 6.05 · Genuine 4.25 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.415 · CE 6.06 · Genuine 4.47 · WER 5.6%

Target 0.404 · CE 6.03 · Genuine 4.41 · WER 0.0%

Target 0.394 · CE 6.19 · Genuine 4.10 · WER 0.0%

Target 0.449 · CE 6.15 · Genuine 4.21 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. 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 Sourness. 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 Sourness. 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 0.405 · CE 6.18 · Genuine 4.52 · WER 0.0%

Target 0.412 · CE 6.11 · Genuine 4.20 · WER 0.0%

Target 0.403 · CE 5.96 · Genuine 4.24 · WER 5.6%

Target 0.420 · CE 6.06 · Genuine 4.42 · WER 0.0%

Spanish

Fixed speaker reference:

ConditionnTarget score ↑Content Enjoyment ↑Genuineness ↑WER ↓
Merged base, no bucket adapter40.345 ± 0.0626.062 ± 0.1794.435 ± 0.2630.00% ± 0.00
Rank32 × 0.540.377 ± 0.0296.054 ± 0.0064.512 ± 0.1430.00% ± 0.00
Rank32 × 0.7540.375 ± 0.0436.068 ± 0.1724.398 ± 0.3050.00% ± 0.00
Rank32 × 1.040.334 ± 0.0396.104 ± 0.0994.347 ± 0.2070.00% ± 0.00
Prompt / seedMerged base · no new LoRARank32 × 0.5Rank32 × 0.75Rank32 × 1.0
Seed 1701

La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.

Exact GENERAL / SCRIPT prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.
(Intense Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.

Target 0.423 · CE 5.90 · Genuine 4.56 · WER 0.0%

Target 0.385 · CE 6.05 · Genuine 4.34 · WER 0.0%

Target 0.434 · CE 5.85 · Genuine 4.41 · WER 0.0%

Target 0.341 · CE 5.96 · Genuine 4.06 · WER 0.0%

Seed 1702

La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.

Exact GENERAL / SCRIPT prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.
(Intense Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.

Target 0.366 · CE 5.91 · Genuine 4.04 · WER 0.0%

Target 0.410 · CE 6.05 · Genuine 4.46 · WER 0.0%

Target 0.383 · CE 6.09 · Genuine 3.97 · WER 0.0%

Target 0.386 · CE 6.17 · Genuine 4.44 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.
(Intense Sourness. 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 Sourness. 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 0.306 · CE 6.22 · Genuine 4.53 · WER 0.0%

Target 0.342 · CE 6.06 · Genuine 4.60 · WER 0.0%

Target 0.346 · CE 6.07 · Genuine 4.56 · WER 0.0%

Target 0.306 · CE 6.16 · Genuine 4.36 · 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 prompt
GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.
SCRIPT:
(Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.
(Intense Sourness. 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 Sourness. 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 0.284 · CE 6.21 · Genuine 4.61 · WER 0.0%

Target 0.369 · CE 6.05 · Genuine 4.66 · WER 0.0%

Target 0.339 · CE 6.27 · Genuine 4.66 · WER 0.0%

Target 0.303 · CE 6.13 · Genuine 4.53 · WER 0.0%