| # | 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
|
|---|---|---|---|---|---|---|
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-Low-Sample-79ll_zh/M0__5.426-5.894
|
I what?
|
|||||
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-Low-Sample-79ll_zh/F0__0.000-1.502
|
Calm down and let me explain.
|
|||||
|
CB-4-min-test-onmv__H_MAGISSA_S01_E004-part1-lowre-d632_el/M0__197.405-198.455
|
Stay out of this.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__202.920-205.432
|
And it will tell everything absolutely correctly.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-1_250310-hdwk_ko/F2__809.934-810.888
|
How old were you again?
|
|||||
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-Low-Sample-79ll_zh/M0__11.353-12.654
|
So that's why you're so famous.
|
|||||
|
CB-WINGED-TES-1jcc__vlc-record-2025-03-31-09h49m41-06pp_pt/F0__11.169-14.082
|
They will have to show up with this girl at some point.
|
|||||
|
IYUNORobin_Samp-gdya__Robin_Sample-5dha_ko/F0__31.761-32.915
|
I said don't move!
|
|||||
|
DC-Profession-nwje__Folge-5-Vanessa-djwo_de/F0__84.948-87.893
|
When you're on the open road, you get a real sense of freedom.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__601.057-604.773
|
There's been a huge misunderstanding. Please take me to your king.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-1_250310-hdwk_ko/F1__236.585-238.383
|
And I wore my new coat today too.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-2_250310-yjrn_ko/M5__1294.014-1295.923
|
I'll go upstairs to clean the roasting room.
|
|||||
|
CB-4-min-test-onmv__H_MAGISSA_S01_E004-part1-lowre-d632_el/M0__146.875-149.455
|
You will also return all his belongings...
|
|||||
|
IYUNOTTS-Manage-wvxp__Unmaksed-sample-2-video-2xs8_ko/F1__11.835-12.307
|
Sir
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/M1__219.140-223.781
|
My king, sometimes people only want to hear good things from Paro.
|
|||||
|
DC-Profession-nwje__Folge-7-Melanie-ynct_de/F0__61.507-64.980
|
To be honest, it was actually quite crazy when I first came back to work.
|
|||||
|
DC-Profession-nwje__Folge-1-Astar-yejb_de/F0__163.735-168.182
|
And I sent the photo to my friends as soon as I could saying, 'Guys, look what's happening here.'
|
|||||
|
IYUNOKOEN-Exter-u6bj__-5-3xfn_ko/M0__131.695-132.438
|
It's truffle.
|
|||||
|
IYUNOKOEN-Exter-u6bj__-5-3xfn_ko/M0__296.373-297.934
|
The crunchy sound is insane.
|
|||||
|
CB-MARTIAL-AV-bar3__MARTIAL-AVENGER-TEST-VIDEO-6b5w-clone-718c_it/M1__82.610-83.672
|
but I assure you
|