| # | uttid | text |
baseline
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: yt4_diff_seed_vc_unnorm_mels_40k
lang: es
meta:
basket_generation_config:
basket_lang: es
basket_path: /home/user/v2v/quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
batch_size: 1
gpus: 4
inference:
diff_k: 3
diff_steps: 400
exp: /mount/s3/tts-binary-data-nb/polovick/exp/yt4_diff_seed_vc_unnorm_mels_40k
gpt_generate_args:
do_sample: true
num_return_sequences: 50
use_cache: true
override_conditioning_features:
bad_text_proba: 0.0
c50: 0.0
pitch_std: 100.0
snr: 100.0
reranking_options:
mode: MBR
top_k: 1
target_len_rate: 0.75
vocoder: bigvgan
voice_samples_preprocessing:
- demucs
- deepfilternet
num_workers: 1
output_dir: dsat_basket/yt4_diff_seed_vc_unnorm_mels_40k__2024-10-30_16-13-40
ticket: ABC-123
basket_generation_git_hash: b12c0445eb8945bffbe718d1db06d035ee3dc405
model_data_type: tts-cloning
ticket: ABC-123
version: 2024-10-30_16-13-40
|
baseline-old-diff
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
|
wavtok
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: gpt_defaultparams
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: 100
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_wavtok_inhouse/gpt_defaultparams/
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty: 3.0
repetition_penalty_activation_span: 2.0
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_wavtok_inhouse_nonorm/gpt_defaultparams__2024-11-26_14-11-07
ticket: TTS-392
basket_generation_git_hash: 7411c8d2f9b7ef2384f924f4b0f97566f8bc7899
model_data_type: tts-cloning
ticket: TTS-392
version: 2024-11-26_14-11-07
|
wavtok-diff
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: gpt_defaultparams__diff
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: 100
diffusion_exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_wavtok_inhouse/diff
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_wavtok_inhouse/gpt_defaultparams/
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty: 3.0
repetition_penalty_activation_span: 2.0
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: bigvgan
num_workers: 1
output_dir: es_en_clean-dsat_mapping_wavtok_inhouse_nonorm/gpt_defaultparams__diff__2024-11-26_14-13-08
ticket: TTS-392
basket_generation_git_hash: 7411c8d2f9b7ef2384f924f4b0f97566f8bc7899
model_data_type: tts-cloning
ticket: TTS-392
version: 2024-11-26_14-13-08
|
wavtok-diff_resampled
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_5projects_cleared_721.json
data_meta: null
exp_name: gpt_defaultparams__diff_resampled
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: 100
diffusion_exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_wavtok_inhouse/diff_resampled/
exp: /mount/s3/tts-binary-data-nb/dimdi-y/yt4_wavtok_inhouse/gpt_defaultparams/
gpt_generate_args:
do_sample: true
num_return_sequences: 50
repetition_penalty: 3.0
repetition_penalty_activation_span: 2.0
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: bigvgan
num_workers: 1
output_dir: es_en_clean-dsat_mapping_wavtok_inhouse_nonorm/gpt_defaultparams__diff_resampled__2024-11-26_14-19-35
ticket: TTS-392
basket_generation_git_hash: 7411c8d2f9b7ef2384f924f4b0f97566f8bc7899
model_data_type: tts-cloning
ticket: TTS-392
version: 2024-11-26_14-19-35
|
|---|---|---|---|---|---|---|---|
|
120
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0034
|
What neighborhood am I from?
|
|||||
|
121
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0035
|
Well, I grew up in the Marqués de Salamanca neighborhood.
|
|||||
|
122
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4_0036
|
I told you.
|
|||||
|
123
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F6/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F6_0037
|
My name is Adela.
|
|||||
|
124
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0038
|
Hello Adela, how are you?
|
|||||
|
125
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F6/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F6_0039
|
Hello.
|
|||||
|
126
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0040
|
Pleased to meet you.
|
|||||
|
127
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0041
|
Well, you were working on the accented words, weren't you? The acute ones... There are the acute ones, there are the flat ones...
|
|||||
|
128
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0043
|
Tell me.
|
|||||
|
129
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F4_0044
|
And why doesn't Amparo continue?
|
|||||
|
130
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0045
|
Because... there's been a little change and... and this morning I'm going to stay.
|
|||||
|
131
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5_0046
|
But are you a teacher or what?
|
|||||
|
132
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0047
|
Yes, I am a teacher, I studied teaching.
|
|||||
|
133
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0048
|
May I have a moment, please?
|
|||||
|
134
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0049
|
The acute words, the... Please, just a moment... Just a moment... I understand... I understand that you prefer the other teacher because you don't know me at all...
|
|||||
|
135
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0050
|
I have just arrived.
|
|||||
|
136
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0051
|
But maybe I can show you something.
|
|||||
|
137
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0052
|
And I'm sure you can teach me something.
|
|||||
|
138
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5_0053
|
A lot.
|
|||||
|
139
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0054
|
I'm sure it is, I'm sure it is a lot.
|
|||||
|
140
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0055
|
But what I think is that... we have to do it together.
|
|||||
|
141
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F7/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F7_0056
|
Us and those in the Salamanca neighborhood.
|
|||||
|
142
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0057
|
Well, be that as it may, I think the most important thing is that we respect each other.
|
|||||
|
143
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0058
|
Because if we do not respect ourselves, how can we pretend to be respectable to others?
|
|||||
|
144
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0059
|
I really feel that this way... we can all be much stronger.
|
|||||
|
145
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0060
|
And... alas...
|
|||||
|
146
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0_0061
|
Amelia! Come!
|
|||||
|
147
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0_0062
|
Come!
|
|||||
|
148
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0_0063
|
This is Amelia; she is a friend.
|
|||||
|
149
|
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_M0_0064
|
Jean?
|