| # | 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
|
|---|---|---|---|---|---|---|---|---|
|
90
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0004
|
Hello?
|
||||||
|
91
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0005
|
What do you want?
|
||||||
|
92
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0006
|
Well, we came here because you said the townhouse was open to everyone....
|
||||||
|
93
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0007
|
Well, all workers.
|
||||||
|
94
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0008
|
She is not.
|
||||||
|
95
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3_0009
|
I can help if you need anything.
|
||||||
|
96
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0010
|
Help with what?
|
||||||
|
97
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3_0011
|
I don't know.
|
||||||
|
98
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3_0012
|
I can teach.
|
||||||
|
99
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0013
|
Of what?
|
||||||
|
100
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3_0014
|
French, for example.
|
||||||
|
101
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0015
|
De fran...
|
||||||
|
102
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0016
|
Ouch!
|
||||||
|
103
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0017
|
But here they don't even know how to read Spanish.
|
||||||
|
104
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3_0018
|
Well, I can teach them.
|
||||||
|
105
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F2/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F2_0019
|
Yes, he has studied to be a teacher.
|
||||||
|
106
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0020
|
Already.
|
||||||
|
107
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0021
|
Come!
|
||||||
|
108
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0022
|
Good morning.
|
||||||
|
109
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4_0023
|
Good morning.
|
||||||
|
110
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0024
|
Girls, there is going to be a small change.
|
||||||
|
111
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0025
|
Amparo leaves with other students and you stay with the new teacher.
|
||||||
|
112
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0026
|
Be good.
|
||||||
|
113
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F3_0027
|
But it is not necessary that...
|
||||||
|
114
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0028
|
We're leaving, girls! Your students.
|
||||||
|
115
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0029
|
Hello.
|
||||||
|
116
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0030
|
Well, I'm Amelia.
|
||||||
|
117
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4_0031
|
Where are you from?
|
||||||
|
118
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0032
|
From... Madrid
|
||||||
|
119
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5_0033
|
Madrid is very large.
|