| # | uttid | text |
baseline
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_baseline_lats
lang: en
meta:
basket_generation_config:
basket_lang: en
basket_path: /home/polovick/v2v_diff/ml/projects/ai-voice-cloning/dsat-basket-extended-refs-dur.json
batch_size: 1
gpus: 2
inference:
diff_steps: 400
exp: /home/polovick/v2v_diff/ml/projects/ai-voice-cloning/yt4_baseline_lats
gpt_generate_args:
do_sample: true
num_return_sequences: 50
override_conditioning_features:
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 0.75
vocoder: univnet
num_workers: 1
output_dir: dsat-cleared/yt4_baseline_lats__2024-07-30_03-28-45
ticket: QUALITY-54
basket_generation_git_hash: e0df79f1213deffbae77e909499694944e0746da
model_data_type: tts-cloning
ticket: QUALITY-54
version: 2024-07-30_03-28-45
|
encodec-inhousediff-sameinfer
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_langbycond_revgrad1_encodec-opt-bigbatch-diffcodes__diff_nonorm_2codes_pretrained
lang: en
meta:
basket_generation_config:
basket_lang: en
basket_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_on_codes: false
diff_steps: 400
diffusion_exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_langbycond_revgrad1-contrastive_encodec-opt-bigbatch_normloudness_delaypattern8/diff_nonorm_2codes_pretrained
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_langbycond_revgrad1_encodec-opt-bigbatch-diffcodes
gpt_generate_args:
do_sample: true
num_return_sequences: 50
prefix_allowed_tokens_fn: encodec_interleaved_layers
repetition_penalty_activation_span: 4.0
repetition_penalty_span: 50.0
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
cdist_time_downsampling_factor: 2
mode: MBR
sakoe_chiba_radius: 24
top_k: 1
vocoder: bigvgan
num_workers: 1
output_dir: es_en_clean-dsat_mapping_encodec_mbrlat_inhdiff/yt4_langbycond_revgrad1_encodec-opt-bigbatch-diffcodes__diff_nonorm_2codes_pretrained__2024-09-18_17-36-55
ticket: TTS-393
basket_generation_git_hash: 75e464c6d886d92ef5b904f41695658ca2bc7545
model_data_type: tts-cloning
ticket: TTS-393
version: 2024-09-18_17-36-55
|
xcodec160k_1code_inhdiff20k
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_langbycond_revgrad1_xcodec-opt-bigbatch__diffusion_yt4_xcodec
lang: en
meta:
basket_generation_config:
basket_lang: en
basket_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_on_codes: true
diff_steps: 400
diffusion_exp: /mount/s3/tts-binary-data-nb/dimdi-y/diffusion_yt4_xcodec
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_langbycond_revgrad1_xcodec-opt-bigbatch
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty_activation_span: 4.0
repetition_penalty_span: 50.0
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
sakoe_chiba_radius: 16
top_k: 1
vocoder: bigvgan
num_workers: 1
output_dir: es_en_clean-dsat_mapping_xcodec_mbrlat_inhdiff/yt4_langbycond_revgrad1_xcodec-opt-bigbatch__diffusion_yt4_xcodec__2024-10-02_15-50-47
ticket: TTS-393
basket_generation_git_hash: 75e464c6d886d92ef5b904f41695658ca2bc7545
model_data_type: tts-cloning
ticket: TTS-393
version: 2024-10-02_15-50-47
|
wavtokeniser
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc
lang: en
meta:
basket_generation_config:
basket_lang: en
basket_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_on_codes: true
diff_steps: 400
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty_activation_span: 1.0
repetition_penalty_span: 100.0
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
sakoe_chiba_radius: 24
top_k: 1
vocoder: none
num_workers: 1
output_dir: es_en_clean-dsat_mapping_xcodec_mbrlat_codecdec/yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc__2024-10-29_09-42-52
ticket: TTS-392
basket_generation_git_hash: 75e464c6d886d92ef5b904f41695658ca2bc7545
model_data_type: tts-cloning
ticket: TTS-392
version: 2024-10-29_09-42-52
|
wavtokeniser_normloud
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc
lang: en
meta:
basket_generation_config:
basket_lang: en
basket_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_on_codes: true
diff_steps: 400
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc
force_reference_std: -23
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty_activation_span: 1.0
repetition_penalty_span: 100.0
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
sakoe_chiba_radius: 24
top_k: 1
vocoder: none
num_workers: 1
output_dir: es_en_clean-dsat_mapping_xcodec_mbrlat_codecdec/yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc__2024-10-29_09-58-08
ticket: TTS-392
basket_generation_git_hash: 75e464c6d886d92ef5b904f41695658ca2bc7545
model_data_type: tts-cloning
ticket: TTS-392
version: 2024-10-29_09-58-08
|
wavtokeniser_normloud_lesspenalty
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc
lang: en
meta:
basket_generation_config:
basket_lang: en
basket_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
batch_size: 1
gpus: 1
inference:
condition_sample_rate: 24000
diff_on_codes: true
diff_steps: 400
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc
force_reference_std: -23
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty: 1.5
repetition_penalty_activation_span: 5.0
repetition_penalty_span: 100.0
use_cache: true
out_sample_rate: 24000
override_conditioning_features:
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
sakoe_chiba_radius: 24
top_k: 1
vocoder: none
num_workers: 1
output_dir: es_en_clean-dsat_mapping_xcodec_mbrlat_codecdec/yt4_langbycond_revgrad1_wavtokenizer-opt-bigbatch_t5enc__2024-10-29_13-45-07
ticket: TTS-392
basket_generation_git_hash: 75e464c6d886d92ef5b904f41695658ca2bc7545
model_data_type: tts-cloning
ticket: TTS-392
version: 2024-10-29_13-45-07
|
|---|---|---|---|---|---|---|---|---|
|
480
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0097
|
I can travel, have powerful men, but I-I want my life back.
|
||||||
|
481
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0098
|
What about that coin, then?
|
||||||
|
482
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0099
|
I...
|
||||||
|
483
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0100
|
I needed you to come here to me.
|
||||||
|
484
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0101
|
That's why I left you that coin.
|
||||||
|
485
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0102
|
You are the only person who can help me, Katherine.
|
||||||
|
486
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0103
|
We can stop this.
|
||||||
|
487
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0104
|
Can we do this again?
|
||||||
|
488
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0105
|
No, no, no phones.
|
||||||
|
489
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0106
|
Only you can help me.
|
||||||
|
490
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0107
|
I...would like to... I'm trying....
|
||||||
|
491
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0108
|
Really, I would like to...
|
||||||
|
492
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0109
|
Sorry.
|
||||||
|
493
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0111
|
Excuse me, is Katherine in there?
|
||||||
|
494
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0112
|
Look, I'm sorry.
|
||||||
|
495
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0113
|
I just want to know if you're okay, okay?
|
||||||
|
496
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0114
|
What does he know?
|
||||||
|
497
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0115
|
Huh?
|
||||||
|
498
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0116
|
Nothing, nothing.
|
||||||
|
499
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0117
|
You don't have to do anything.
|
||||||
|
500
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0119
|
Clear?
|
||||||
|
501
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0120
|
I don't want to involve anyone, but if I have to, I will.
|
||||||
|
502
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0121
|
He doesn't know anything, I swear.
|
||||||
|
503
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0122
|
He just saw the note.
|
||||||
|
504
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0123
|
Cat, please tell me something.
|
||||||
|
505
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0124
|
However, if he doesn't hear from me, he will know that something is wrong.
|
||||||
|
506
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0125
|
You will not tell her anything.
|
||||||
|
507
|
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0126
|
No, no!
|
||||||
|
508
|
LA6_Full_ProresHQ-2-_it_F2/LA6_Full_ProresHQ-2-_it_F2_0127
|
You won't have to tell her I have to run, you won't have to tell about the police, you won't have to say anything.
|
||||||
|
509
|
LA6_Full_ProresHQ-2-_it_F1/LA6_Full_ProresHQ-2-_it_F1_0128
|
No no no, I swear to you, I swear to you.
|