| # | uttid | text | ref |
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
|
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
|
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
|
idxdistill1
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_finetune_idxdistill_lora__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_finetune_idxdistill_lora
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_finetune_idxdistill_lora__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-02-13_11-54-47
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: a0fff333bc707fa86bab206dec923bbfe5b51d8c
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-02-13_11-54-47
|
idxdistill2
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_finetune_idxdistill_lora__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_finetune_idxdistill_lora
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: 100.0
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_finetune_idxdistill_lora__yt4_wavtokenizer_16K_lossent0.15_indexrefencoder_separate_self__2026-02-13_12-07-53
ref_dir: cc_20250825/ref
ticket: QUALITY-41
basket_generation_git_hash: a0fff333bc707fa86bab206dec923bbfe5b51d8c
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2026-02-13_12-07-53
|
|---|---|---|---|---|---|---|---|---|
|
DF-creative-commons-basket/03VPqxrlyxA_zh/F1__8.234-8.922
|
Every second.
|
|||||||
|
DF-creative-commons-basket/b91pBJWJDhQ_ru/M0__9.240-10.650
|
Please forgive me.
|
|||||||
|
DF-creative-commons-basket/CDxg_6317fA_ja/M1__4.346-5.698
|
Don't tell anyone.
|
|||||||
|
DF-creative-commons-basket/l-l9x4bLVUY_zh/F0__11.480-13.480
|
It's all perfectly normal.
|
|||||||
|
DF-creative-commons-basket/5Ges6LpYtI0_it/M0__9.020-10.034
|
Ah, did you quarrel?
|
|||||||
|
DF-creative-commons-basket/jdSyxrG6dfM_it/M0__8.400-9.490
|
But I have a helmet.
|
|||||||
|
DF-creative-commons-basket/pr5WOuKPrus_hi/F0__11.240-12.820
|
I won't let you go.
|
|||||||
|
DF-creative-commons-basket/DGbTKywfSxw_ru/F0__10.360-12.490
|
What's troubling you, son?
|