Prev
# uttid text ref baseline
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
data_meta: null
exp_name: yt4_bad_text_proba
lang: en
meta:
  basket_generation_config:
    basket_lang: en
    basket_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
    batch_size: 4
    gpus: 2
    inference:
      condition_sample_rate: 24000
      diff_k: 3
      diff_steps: 100
      duplicate_reference: true
      exp: /mount/s3/tts-binary-data-nb/slave/exp/yt4_bad_text_proba/
      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: 1.25
      vocoder: bigvgan
      voice_samples_preprocessing:
      - demucs
      - deepfilternet
    num_workers: 1
    output_dir: dsat_to_en_mini/yt4_bad_text_proba__2025-01-20_17-25-48
    ticket: QUALITY-41
  basket_generation_git_hash: 6f6cb768a4ef7425185fdde6d1a4eac9371eb37e
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-01-20_17-25-48
esesla_enusgbcain
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
data_meta: null
exp_name: yt4_consistency_esesla_3_enusgbcainau_revgrad
lang: en-us
meta:
  basket_generation_config:
    basket_lang: en-us
    basket_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
    batch_size: 4
    gpus: 2
    inference:
      condition_sample_rate: 24000
      diff_k: 3
      diff_steps: 100
      duplicate_reference: true
      exp: /mount/s3/tts-binary-data-nb/eg/exp/yt4_consistency_esesla_3_enusgbcainau_revgrad/
      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: 1.25
      vocoder: bigvgan
      voice_samples_preprocessing:
      - demucs
      - deepfilternet
    num_workers: 1
    output_dir: dsat_to_en_mini/yt4_consistency_esesla_3_enusgbcainau_revgrad__2025-01-20_17-21-38
    ticket: QUALITY-41
  basket_generation_git_hash: 6f6cb768a4ef7425185fdde6d1a4eac9371eb37e
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-01-20_17-21-38
newlangs
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
data_meta: null
exp_name: gpt_text_consistency_newlangs
lang: en
meta:
  basket_generation_config:
    basket_lang: en
    basket_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
    batch_size: 4
    gpus: 2
    inference:
      condition_sample_rate: 24000
      diff_k: 3
      diff_steps: 100
      duplicate_reference: true
      exp: /mount/s3/tts-binary-data-nb/eg/exp/gpt_text_consistency_newlangs/
      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: 1.25
      vocoder: bigvgan
      voice_samples_preprocessing:
      - demucs
      - deepfilternet
    num_workers: 1
    output_dir: dsat_to_en_mini/gpt_text_consistency_newlangs__2025-01-20_17-29-59
    ticket: QUALITY-41
  basket_generation_git_hash: 6f6cb768a4ef7425185fdde6d1a4eac9371eb37e
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-01-20_17-29-59
enonly
basket_config_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
data_meta: null
exp_name: text_consistency_enonly
lang: en
meta:
  basket_generation_config:
    basket_lang: en
    basket_path: quality/tts/tortoise-baskets/dsat_to_en_mini_100.json
    batch_size: 4
    gpus: 2
    inference:
      condition_sample_rate: 24000
      diff_k: 3
      diff_steps: 100
      duplicate_reference: true
      exp: /mount/s3/tts-binary-data-nb/eg/exp/text_consistency_enonly/
      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: 1.25
      vocoder: bigvgan
      voice_samples_preprocessing:
      - demucs
      - deepfilternet
    num_workers: 1
    output_dir: dsat_to_en_mini/text_consistency_enonly__2025-01-20_17-34-11
    ticket: QUALITY-41
  basket_generation_git_hash: 6f6cb768a4ef7425185fdde6d1a4eac9371eb37e
model_data_type: tts-cloning
ticket: QUALITY-41
version: 2025-01-20_17-34-11
3280
Xdx0wUeDaD8_001/dfdaccf6
3281
V5QzJTUpi3Q_001/163d66a2_24Khz
3282
AdJqgKJgS30_001/c7b3f1f3_24Khz
3283
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...
3284
pcEdR90tbvo_001/9b082eff
3285
TEDX_M_054/TEDX_M_054_SPA_0014
3286
Rosa_de_Guadalupe_-_-56007d_es_M1/Rosa_de_Guadalupe_-_-56007d_es_M1_0129
Come on, Emmanuel, who is running you around?
3287
LA6_Full_ProresHQ-2-_it_F0/LA6_Full_ProresHQ-2-_it_F0_0140
3288
8x6EsAnAGXs_001/7545fd37_24Khz
3289
AdJqgKJgS30_002/a5eb4f12
3290
TEDX_M_046/TEDX_M_046_SPA_0010
3291
PT2m9lkGhvM_001/f87d1233
3292
JVANHaGv21I_001/b76dfd31
3293
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F6/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F6_0037
3294
rZMIQKa-dbo_001/7e1ae226
3295
oR3740vYf-g_001/7fc54102_24Khz
3296
ooXuYlYu6pU_001/4d3b138e
3297
2E6fOjn5ZXU_001/1029d11a
3298
i_107DxLHvE_001/f8110556_24Khz
3299
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F0_0025
Next