| # | uttid | text |
baseline
basket_config_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
data_meta: null
exp_name: gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_k: 3
diff_steps: 100
disable_optimized_diffusion: true
exp: /mount/s3/tts-binary-data-nb/dchebakov/models/gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice/
gpt_generate_args:
do_sample: true
enforce_silent_start: wavtokenizer
num_return_sequences: 50
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
bad_text_proba: 0.0
c50: 0.0
dmcs_flatness: 100500.0
dmcs_roll_off_0.995: 100500.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing:
- deepfilternet
num_workers: 1
output_dir: dsat_042025_to_en_mini/gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice__2025-07-07_09-23-19
ref_dir: dsat_042025_to_en_mini/ref
ticket: QUALITY-41
basket_generation_git_hash: e961ea383299ff424f66fd9505a4c7b12ba65799
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-07-07_09-23-19
|
freq_feats
basket_config_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
data_meta: null
exp_name: gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice__diffusion_yt4_wavtokenizer_freq_feats_noref
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_k: 3
diff_steps: 100
diffusion_exp: /mount/s3/tts-binary-data-nb/eg/exp/diffusion_yt4_wavtokenizer_freq_feats_noref/
disable_optimized_diffusion: true
exp: /mount/s3/tts-binary-data-nb/dchebakov/models/gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice/
gpt_generate_args:
do_sample: true
enforce_silent_start: wavtokenizer
num_return_sequences: 50
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
bad_text_proba: 0.0
c50: 0.0
dmcs_flatness: 100500.0
dmcs_roll_off_0.995: 100500.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing:
- deepfilternet
num_workers: 1
output_dir: dsat_042025_to_en_mini/gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice__diffusion_yt4_wavtokenizer_freq_feats_noref__2025-07-07_09-23-20
ref_dir: dsat_042025_to_en_mini/ref
ticket: QUALITY-41
basket_generation_git_hash: e961ea383299ff424f66fd9505a4c7b12ba65799
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-07-07_09-23-20
|
freq_feats_cv
basket_config_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
data_meta: null
exp_name: gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice__diffusion_yt4_wavtokenizer_freq_feats_noref_condcv
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_k: 3
diff_steps: 100
diffusion_exp: /mount/s3/tts-binary-data-nb/eg/exp/diffusion_yt4_wavtokenizer_freq_feats_noref_condcv/
disable_optimized_diffusion: true
exp: /mount/s3/tts-binary-data-nb/dchebakov/models/gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice/
gpt_generate_args:
do_sample: true
enforce_silent_start: wavtokenizer
num_return_sequences: 50
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
bad_text_proba: 0.0
c50: 0.0
dmcs_flatness: 100500.0
dmcs_roll_off_0.995: 100500.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing:
- deepfilternet
num_workers: 1
output_dir: dsat_042025_to_en_mini/gpt_yt4_langbycond_25freq_fsq_entropy__noclearvoice__diffusion_yt4_wavtokenizer_freq_feats_noref_condcv__2025-07-07_09-23-19
ref_dir: dsat_042025_to_en_mini/ref
ticket: QUALITY-41
basket_generation_git_hash: e961ea383299ff424f66fd9505a4c7b12ba65799
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-07-07_09-23-19
|
dvae_freq_feats
basket_config_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
data_meta: null
exp_name: yt4_en_accent_clf_entropy_t5__diffusion_yt4_en_accent_clf_entropy_t5_freq_feats_EN_noref
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/dsat_042025_to_en_mini_100.json
batch_size: 1
gpus: 1
inference:
diff_k: 3
diff_steps: 100
diffusion_exp: /mount/s3/tts-binary-data-nb/eg/exp/diffusion_yt4_en_accent_clf_entropy_t5_freq_feats_EN_noref/
disable_optimized_diffusion: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_en_accent_clf_entropy_t5/
gpt_generate_args:
do_sample: true
enforce_silent_start: true
num_return_sequences: 50
use_cache: true
override_conditioning_features:
bad_text_proba: 0.0
c50: 0.0
dmcs_flatness: 100500.0
dmcs_roll_off_0.995: 100500.0
pitch_std: 100500.0
snr: 100500.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing:
- deepfilternet
num_workers: 1
output_dir: dsat_042025_to_en_mini/yt4_en_accent_clf_entropy_t5__diffusion_yt4_en_accent_clf_entropy_t5_freq_feats_EN_noref__2025-06-02_13-57-41
ref_dir: dsat_042025_to_en_mini/ref
ticket: QUALITY-41
basket_generation_git_hash: c185fc1cf93b68974cf48ed189a1c77d4535cc35
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-06-02_13-57-41
|
|---|---|---|---|---|---|---|
|
CB-Chinese-mi-idgm__CHINESE_DUBBING_VIDEO-kni9_zh/F1__1.826-2.451
|
Enough!!
|
|||||
|
IYUNOTVing-Samp-j0cw__8a54b337953662d301953bc26c792f-6j3a_ko/M1__154.099-154.658
|
Shall we?
|
|||||
|
IYUNOBokyeom-TV-od3h__Bo-chelin-at-Mingles_Final-29-6euy_ko/M0__274.204-274.825
|
It's in there.
|
|||||
|
DC-Canal-Test-fnv1__NIABLA-25fps-FRA-CLIP-4kln_fr/F1__256.995-258.748
|
My only family was Dad and...
|
|||||
|
CB-4-min-test-onmv__H_MAGISSA_S01_E004-part1-lowre-d632_el/M0__143.981-145.799
|
We'll let it dry and let the sea take it.
|
|||||
|
IYUNOKOEN-Exter-u6bj__-5-l31w_ko/M0__134.121-136.308
|
Among the scents that can be smelled in the human world,
|
|||||
|
IYUNOKOEN-Exter-u6bj__-5-l31w_ko/M0__236.274-238.535
|
While being accessible to the general public,
|
|||||
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-Low-Sample-79ll_zh/F0__3.494-4.916
|
Honey, it's not what you think.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-2_250310-yjrn_ko/F0__1087.571-1088.541
|
Yes, you dummy.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-1_250310-hdwk_ko/F1__1471.435-1472.729
|
Don't you like babies, honey?
|
|||||
|
DC-Test-Russe-alk2__Test-Russe-en-Chinois-9eow_ru/M0__173.662-174.373
|
Well, almost.
|
|||||
|
CB-WINGED-TES-1jcc__vlc-record-2025-03-31-09h49m41-06pp_pt/F3__130.372-135.049
|
and this is actually the reason why you have a scar in the middle of your tiny little tummy.
|
|||||
|
DC-Profession-nwje__Folge-2-Marius-ujwo_de/M0__43.072-53.282
|
In other words, instead of pulling together in the same direction and working as a team with colleagues, people often worked against each other, and there was a lot of envy and resentment on a personal level.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-1_250310-hdwk_ko/F1__1401.627-1402.605
|
If you work hard there,
|
|||||
|
IYUNOBlank-POC-adsh__1-_-AI-_0217-altr_ko/M0__25.535-33.112
|
Before becoming roommates, Jun-saw and Woo-bin had been close friends since childhood, and they moved in together as they started college at the same university.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-2_250310-yjrn_ko/F0__307.002-308.279
|
Yup. What are you up to?
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__1265.478-1266.654
|
Should be returned.
|
|||||
|
IYUNOTTS-Traini-xc4c__Bo-chelin-at-Mingles_Final-29-vf2x_ko/M0__615.618-616.519
|
I feel relieved.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-1_250310-hdwk_ko/F1__1652.277-1652.569
|
||||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__1065.313-1068.348
|
Dholakpur knows only one king. And that is you.
|