| # | uttid | text | ref |
baseline_tgtlen
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15__yt4_wavtokenizer_16K_lossent0.15
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 0.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15__yt4_wavtokenizer_16K_lossent0.15__2026-01-19_14-20-36
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-19_14-20-36
|
indextts2 |
literategoggles_idxdistill
basket_config_path: /mount/s3/tts-binary-data-nb/dchebakov/metrics/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_idxdistill_1ref_emo
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: /mount/s3/tts-binary-data-nb/dchebakov/metrics/tortoise-baskets/cc_20250825_en-US.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_k: 3
diff_steps: 100
duplicate_reference: false
exp: /mount/s3/tts-binary-data-nb/dchebakov/models/yt4_wavtokenizer_16K_lossent0.15_idxdistill_1ref_emo
gpt_generate_args:
do_sample: true
enforce_silent_start: false
num_return_sequences: 30
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
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825_en-US/yt4_wavtokenizer_16K_lossent0.15_idxdistill_1ref_emo__2026-01-10_07-59-19
ref_dir: cc_20250825_en-US/ref
ticket: QUALITY-000
basket_generation_git_hash: 084ccc0c4313e646e3630e4e5a35b7e04d70fdad
model_data_type: tts-cloning
ticket: QUALITY-000
version: 2026-01-10_07-59-19
|
indexrefencoder_ft_enus
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies2_finetune_full_v2__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies2_finetune_full_v2
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 0.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies2_finetune_full_v2__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-01-23_13-08-47
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-23_13-08-47
|
movies2_finetune_closest_anim
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_movies2_finetune_closest__yt4_wavtokenizer_16K_lossent0.15
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_movies2_finetune_closest
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 1.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 1.0
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_movies2_finetune_closest__yt4_wavtokenizer_16K_lossent0.15__2026-01-14_17-25-18
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-14_17-25-18
|
baseline
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15__yt4_wavtokenizer_16K_lossent0.15
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 1.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15__yt4_wavtokenizer_16K_lossent0.15__2026-01-23_18-31-03
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-23_18-31-03
|
indexrefencoder_ft_enus_notgtlen
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies2_finetune_full_v2__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies2_finetune_full_v2
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 0.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies2_finetune_full_v2__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-01-23_17-32-54
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-23_17-32-54
|
movies2_finetune_closest_anim_notgtlen
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_movies2_finetune_closest__yt4_wavtokenizer_16K_lossent0.15
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_movies2_finetune_closest
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 1.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_movies2_finetune_closest__yt4_wavtokenizer_16K_lossent0.15__2026-01-23_18-01-37
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-23_18-01-37
|
indexrefencoder_ft_movies3_closest_enus_notgtlen
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies3_finetune_full_v2_closest__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies3_finetune_full_v2_closest
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 1.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies3_finetune_full_v2_closest__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-01-26_11-26-27
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-26_11-26-27
|
indexrefencoder_ft_movies3_20Kit_closest_enus_notgtlen
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies3_finetune_full_v2_closest__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies3_finetune_full_v2_closest
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 1.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self_movies3_finetune_full_v2_closest__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-01-28_13-09-10
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-28_13-09-10
|
indexrefencoder_noft_enus_notgtlen
basket_config_path: quality/tts/tortoise-baskets/cc_20250825_en-US.json
data_meta: null
exp_name: yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
lang: en-us
meta:
basket_generation_config:
basket_lang: en-us
basket_path: quality/tts/tortoise-baskets/cc_20250825_en-US.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/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
duplicate_reference: true
exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self
gpt_generate_args:
do_sample: true
min_new_tokens: 20
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
emo2vec: null
emotion: null
is_animation: 1.0
pitch_std: 100.0
snr: 100.0
year: 2025.0
reranking_options:
mode: MBR
top_k: 1
vocoder: bigvgan
voice_samples_preprocessing: []
num_workers: 1
output_dir: cc_20250825/yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-01-28_16-42-41
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: 7ba982d9bb8ddc0cb968d517f583b0227d2624ed
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-01-28_16-42-41
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
DF-creative-commons-basket/U_1cQLJKt7c_es/M0__1.240-3.225
|
I know you made me, but I'm going to stop him headfirst.
|
|||||||||||||
|
DF-creative-commons-basket/yFfw234lX0c_zh/M0__0.760-2.160
|
I am crazy!
|
|||||||||||||
|
DF-creative-commons-basket/fVrknIFJBOA_ja/M0__0.176-10.420
|
It's like they might have a script placed in front of the camera or something. They somewhat remember it, but rely on the script while reading. It's that kind of vibe.
|
|||||||||||||
|
DF-creative-commons-basket/rlR9M9QZ4Cg_de/M0__9.245-11.088
|
Everything has always been completely normal.
|
|||||||||||||
|
DF-creative-commons-basket/ZnWNLX4_RV0_de/F0__15.980-17.569
|
I felt like family.
|
|||||||||||||
|
DF-creative-commons-basket/_W3R1g9-ByQ_ru/F0__25.165-28.210
|
Come to me, sweetheart, come to Mommy.
|
|||||||||||||
|
DF-creative-commons-basket/cdExO_qxpLI_hi/F1__17.820-25.301
|
Son, I understand that you love her very much, but this kind of love only lasts for a very short time.
|
|||||||||||||
|
DF-creative-commons-basket/5Ges6LpYtI0_it/F0__5.029-6.105
|
I haven't told him yet.
|
|||||||||||||
|
DF-creative-commons-basket/GLA2YCQi_Rk_fr/F2__9.709-10.987
|
Are you going to lie to her your whole life?
|
|||||||||||||
|
DF-creative-commons-basket/DssUtj_qKf4_ru/F0__17.632-18.770
|
What did you think?
|
|||||||||||||
|
DF-creative-commons-basket/HibKRdG8Ie0_es/F0__14.889-19.659
|
Well, let me tell you that the Charito who stays quiet and puts up with everything has just died.
|
|||||||||||||
|
DF-creative-commons-basket/OesbsUiwgo0_pt/F0__0.000-5.020
|
You'll become famous, rich, but you'll never stop being my servant.
|
|||||||||||||
|
DF-creative-commons-basket/CDxg_6317fA_ja/M2__8.160-9.610
|
You get it, right?!
|
|||||||||||||
|
DF-creative-commons-basket/TxbnBLoS8Ic_zh/F0__0.000-1.740
|
It's the most important thing to me.
|
|||||||||||||
|
DF-creative-commons-basket/jdSyxrG6dfM_it/F0__0.640-2.410
|
Couldn't we make things simpler?
|
|||||||||||||
|
DF-creative-commons-basket/Ljaicg38ZBs_fr/M0__3.190-5.560
|
For this, there's no recipe.
|
|||||||||||||
|
DF-creative-commons-basket/vJEDLWmL_Bg_de/F0__8.580-11.640
|
No, I'd rather go trick-or-treating here with a few friends.
|
|||||||||||||
|
DF-creative-commons-basket/Ll6fcDRKi9k_ru/F0__0.040-1.410
|
I swear on my life!
|
|||||||||||||
|
DF-creative-commons-basket/qJaAnEUiO6E_it/M0__0.110-1.010
|
Sure.
|
|||||||||||||
|
DF-creative-commons-basket/GYW3cASksbw_es/M0__3.480-11.280
|
Today's story reminds us of the two choices we can make when life hits us hard.
|