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
960
a9D45uzJ8Wo_001/b956ef8e_24Khz
961
pcEdR90tbvo_001/dc1653b0_24Khz
962
Cnkmuwcaeuk_001/eac6ce72
963
k5rIMr-u0Jw_001/05da0bcb_24Khz
964
UxxvJldAt9o_001/dcf84e10_24Khz
965
TEDX_F_031/TEDX_F_031_SPA_0001
966
ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5/ORIGINALSPAVERSION-93a5cd-VoiceActing_es_F5_0033
Madrid is very large.
967
sl_JoobohTY_001/de8a7a74_24Khz
968
BdJAZyWbOoo_001/c97c87a2_24Khz
969
8x6EsAnAGXs_001/96383885_24Khz
970
tTFPa4ub4Aw_001/8e7801e7
971
UxxvJldAt9o_001/e8803f14_24Khz
972
A4hPsqqQ8vk_001/8fec6b1e_24Khz
973
y6jOzSdTtjI_002/ba6d0c44
974
XR7cvDLveBU_001/081824b9_24Khz
975
3473/5615f88d
976
DAzDSBKSeBM_001/22c086ae_24Khz
977
eLNfBx3zIoc_001/c16f885b_24Khz
978
y6jOzSdTtjI_001/faa2cff2_24Khz
979
SO9KnCbBNeY_001/3ddff8a1_24Khz
Next