| # | 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
|
|---|---|---|---|---|---|---|
|
IYUNOKonrev_Bla-5xua__Blah-Season-2_250310-yjrn_ko/F0__190.701-191.979
|
That's what I'm afraid of.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__470.103-474.064
|
Being a long-time neighbor of Dholakpur, he knew everything about us.
|
|||||
|
PRESTO--achy-3bnk__sachy_cut-2e66_cs/M0__15.295-18.789
|
Black probably will not have any real chances to play in this position.
|
|||||
|
IYUNOKonrev_Bla-5xua__Soul-Scandal-Season-1_250310-z2ow_ko/F1__46.879-48.949
|
Looks like something urgent came up on the schedule.
|
|||||
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-High-End-ujqs_zh/F0__12.234-13.294
|
A marriage contract.
|
|||||
|
IYUNOTTS-Manage-wvxp__Unmaksed-sample-2-video-2xs8_ko/F1__55.230-56.581
|
I told you to go to a hotel
|
|||||
|
MELSDerniere_s-q0kl__DerniereSeconde_S01-E01_SansPa-auy3_fr/F0__16.907-17.385
|
Yes!
|
|||||
|
IYUNOBokyeom-TV-aqzk__Bo-chelin-at-Mingles_Final-29-1yx9_ko/M0__614.657-615.518
|
I feel relieved.
|
|||||
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-Low-Sample-79ll_zh/M0__72.062-74.624
|
To have such a beautiful flight attendant as my wife.
|
|||||
|
IYUNOKonrev_Bla-5xua__Soul-Scandal-Season-1_250310-z2ow_ko/F5__895.040-896.362
|
You're meeting me right now.
|
|||||
|
CB-4-min-test-onmv__H_MAGISSA_S01_E004-part1-lowre-d632_el/M0__174.825-177.082
|
Give back the coins, Thrasos.
|
|||||
|
DC-Profession-nwje__Folge-10-Sonja-0g8r_de/F0__63.768-69.443
|
My first major project at Hofmann Personal was the restructuring of our subsidiary in the United States.
|
|||||
|
MELSDerniere_s-s478__DerniereSeconde_S01-E01_SansPa-cs7j_fr/F0__19.145-20.832
|
You're lucky I have to pretend to work...
|
|||||
|
DC-Profession-nwje__Folge-9-Yeva-xyya_de/F0__34.996-42.023
|
I started learning German when I was younger because I'd set myself the goal of coming to study here in Germany one day. That's why I could speak German already.
|
|||||
|
IYUNOKonrev_Bla-5xua__Soul-Scandal-Season-1_250310-z2ow_ko/F1__598.447-601.142
|
I'm okay, Teacher. Really, I didn't get hurt at all.
|
|||||
|
MELSDerniere_s-s478__DerniereSeconde_S01-E01_SansPa-cs7j_fr/F0__16.807-17.367
|
Yeah.
|
|||||
|
CB-Chinese-mi-idgm__CHINESE_DUBBING_VIDEO-kni9_zh/F1__81.412-82.564
|
This is outrageous!
|
|||||
|
NINJAtravel-sho-z7ek__FXP_ATKS4_01_delhi_S1-4ttm_hi/M0__18.988-20.023
|
Known as the city of
|
|||||
|
CB-WINGED-TES-1jcc__vlc-record-2025-03-31-09h49m41-06pp_pt/F4__120.527-124.291
|
I don't have any shell to show there and I don't know what to do.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__295.362-296.513
|
Only one rupee.
|