| # | 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
|
|---|---|---|---|---|---|---|
|
IYUNOKOEN-Exter-u6bj__-5-l31w_ko/M0__17.203-19.015
|
Let me explain a bit about the stars.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F1__374.376-376.023
|
Why don't we go and catch him?
|
|||||
|
NETFLIX-test-proje-698i__JP-test-clip-1f6q_pt/M1__358.051-360.164
|
Tell him if he doesn't sign me, he'll lose the best driver.
|
|||||
|
IYUNOBokyeom-TV-od3h__Bo-chelin-at-Mingles_Final-29-6euy_ko/M0__724.231-725.142
|
Oh yes, thank you.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/F2__1108.450-1109.243
|
This is it.
|
|||||
|
CSHARP-DEMO-SAMPL-gnpv__Hindi-High-End-ujqs_zh/F0__35.159-36.681
|
she certainly wouldn't approve of you.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/M4__1026.872-1028.166
|
Go away from here.
|
|||||
|
NINJACB-0k50__Epi-14-Talking-Parrot-Samurai-pmm7_hi/M3__475.530-477.707
|
And Babu said that Batukpur would attack us.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-1_250310-hdwk_ko/F1__20.908-21.654
|
What a jerk.
|
|||||
|
CB-Chinese-mi-idgm__CHINESE_DUBBING_VIDEO-kni9_zh/M4__39.473-41.331
|
whose words are said to be worth a fortune!
|
|||||
|
NINJAtravel-sho-z7ek__FXP_ATKS4_01_delhi_S1-4ttm_hi/M0__20.020-20.957
|
big-hearted people.
|
|||||
|
IYUNOKonrev_Bla-5xua__Blah-Season-2_250310-yjrn_ko/M0__59.348-60.006
|
Jeez.
|
|||||
|
DC-Test-Live--j5dr__Express-5-min-sample-9et1_es/F0__137.671-139.531
|
He went every Wednesday with some friends.
|
|||||
|
DC-Canal-Test-fnv1__NIABLA-25fps-FRA-CLIP-4kln_fr/F1__70.391-72.819
|
But don't tell Mom, ok? It's our secret.
|
|||||
|
DC-Profession-nwje__Folge-4-Radu-gbf6_de/M0__159.503-161.278
|
We're not just coworkers, we're family.
|
|||||
|
IYUNOUnmasked_I-7qyz__Trigger-4-p1n7_ko/F0__24.160-28.410
|
Looks like Han P. D. got a bit worked up yesterday after being accused of killing that cat.
|
|||||
|
IYUNOBokyeom-TV-aqzk__Bo-chelin-at-Mingles_Final-29-1yx9_ko/M0__939.037-940.318
|
If you recommend them in the comments.
|
|||||
|
IYUNOBokyeom-TV-od3h__Bo-chelin-at-Mingles_Final-29-6euy_ko/M0__549.129-550.170
|
Is it a piece of cake?
|
|||||
|
IYUNOBokyeom-TV-od3h__Bo-chelin-at-Mingles_Final-29-6euy_ko/M0__260.205-260.937
|
It's decreasing.
|
|||||
|
CB-MARTIAL-AV-bar3__MARTIAL-AVENGER-TEST-VIDEO-6b5w-clone-718c_it/M1__84.450-85.900
|
I've thought about what you said
|