ESPnet2 pretrained model, kan-bayashi/ljspeech_tts_train_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave, fs=22050, lang=en

This model was trained by kan-bayashi using ljspeech/tts1 recipe in espnet.

• Python API

  See https://github.com/espnet/espnet_model_zoo

• Evaluate in the recipe

  git clone https://github.com/espnet/espnet
  cd espnet
  git checkout 67ca53d61932e4ff3325f1ea7215eead03f300bb
  pip install -e .
  cd egs2/ljspeech/tts1
  # Download the model file here
  ./run.sh --skip_data_prep false --skip_train true --download_model kan-bayashi/ljspeech_tts_train_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
  

• Config

  config: conf/tuning/train_transformer.yaml
  print_config: false
  log_level: INFO
  dry_run: false
  iterator_type: sequence
  output_dir: exp/tts_train_transformer_raw_phn_tacotron_g2p_en_no_space
  ngpu: 1
  seed: 0
  num_workers: 1
  num_att_plot: 3
  dist_backend: nccl
  dist_init_method: env://
  dist_world_size: 4
  dist_rank: 0
  local_rank: 0
  dist_master_addr: localhost
  dist_master_port: 53481
  dist_launcher: null
  multiprocessing_distributed: true
  cudnn_enabled: true
  cudnn_benchmark: false
  cudnn_deterministic: true
  collect_stats: false
  write_collected_feats: false
  max_epoch: 200
  patience: null
  val_scheduler_criterion:
  - valid
  - loss
  early_stopping_criterion:
  - valid
  - loss
  - min
  best_model_criterion:
  -   - valid
      - loss
      - min
  -   - train
      - loss
      - min
  keep_nbest_models: 5
  grad_clip: 1.0
  grad_clip_type: 2.0
  grad_noise: false
  accum_grad: 2
  no_forward_run: false
  resume: true
  train_dtype: float32
  use_amp: false
  log_interval: null
  pretrain_path: []
  pretrain_key: []
  num_iters_per_epoch: 1000
  batch_size: 20
  valid_batch_size: null
  batch_bins: 9000000
  valid_batch_bins: null
  train_shape_file:
  - exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/text_shape.phn
  - exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/speech_shape
  valid_shape_file:
  - exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/valid/text_shape.phn
  - exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/valid/speech_shape
  batch_type: numel
  valid_batch_type: null
  fold_length:
  - 150
  - 204800
  sort_in_batch: descending
  sort_batch: descending
  multiple_iterator: false
  chunk_length: 500
  chunk_shift_ratio: 0.5
  num_cache_chunks: 1024
  train_data_path_and_name_and_type:
  -   - dump/raw/tr_no_dev/text
      - text
      - text
  -   - dump/raw/tr_no_dev/wav.scp
      - speech
      - sound
  valid_data_path_and_name_and_type:
  -   - dump/raw/dev/text
      - text
      - text
  -   - dump/raw/dev/wav.scp
      - speech
      - sound
  allow_variable_data_keys: false
  max_cache_size: 0.0
  valid_max_cache_size: null
  optim: adam
  optim_conf:
      lr: 1.0
  scheduler: noamlr
  scheduler_conf:
      model_size: 512
      warmup_steps: 8000
  token_list:
  - 
  - 
  - AH0
  - N
  - T
  - D
  - S
  - R
  - L
  - DH
  - K
  - Z
  - IH1
  - IH0
  - M
  - EH1
  - W
  - P
  - AE1
  - AH1
  - V
  - ER0
  - F
  - ','
  - AA1
  - B
  - HH
  - IY1
  - UW1
  - IY0
  - AO1
  - EY1
  - AY1
  - .
  - OW1
  - SH
  - NG
  - G
  - ER1
  - CH
  - JH
  - Y
  - AW1
  - TH
  - UH1
  - EH2
  - OW0
  - EY2
  - AO0
  - IH2
  - AE2
  - AY2
  - AA2
  - UW0
  - EH0
  - OY1
  - EY0
  - AO2
  - ZH
  - OW2
  - AE0
  - UW2
  - AH2
  - AY0
  - IY2
  - AW2
  - AA0
  - ''''
  - ER2
  - UH2
  - '?'
  - OY2
  - '!'
  - AW0
  - UH0
  - OY0
  - ..
  - 
  odim: null
  model_conf: {}
  use_preprocessor: true
  token_type: phn
  bpemodel: null
  non_linguistic_symbols: null
  cleaner: tacotron
  g2p: g2p_en_no_space
  feats_extract: fbank
  feats_extract_conf:
      fs: 22050
      fmin: 80
      fmax: 7600
      n_mels: 80
      hop_length: 256
      n_fft: 1024
      win_length: null
  normalize: global_mvn
  normalize_conf:
      stats_file: exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/feats_stats.npz
  tts: transformer
  tts_conf:
      embed_dim: 0
      eprenet_conv_layers: 0
      eprenet_conv_filts: 0
      eprenet_conv_chans: 0
      dprenet_layers: 2
      dprenet_units: 256
      adim: 512
      aheads: 8
      elayers: 6
      eunits: 1024
      dlayers: 6
      dunits: 1024
      positionwise_layer_type: conv1d
      positionwise_conv_kernel_size: 1
      postnet_layers: 5
      postnet_filts: 5
      postnet_chans: 256
      use_masking: true
      bce_pos_weight: 5.0
      use_scaled_pos_enc: true
      encoder_normalize_before: true
      decoder_normalize_before: true
      reduction_factor: 1
      init_type: xavier_uniform
      init_enc_alpha: 1.0
      init_dec_alpha: 1.0
      eprenet_dropout_rate: 0.0
      dprenet_dropout_rate: 0.5
      postnet_dropout_rate: 0.5
      transformer_enc_dropout_rate: 0.1
      transformer_enc_positional_dropout_rate: 0.1
      transformer_enc_attn_dropout_rate: 0.1
      transformer_dec_dropout_rate: 0.1
      transformer_dec_positional_dropout_rate: 0.1
      transformer_dec_attn_dropout_rate: 0.1
      transformer_enc_dec_attn_dropout_rate: 0.1
      use_guided_attn_loss: true
      num_heads_applied_guided_attn: 2
      num_layers_applied_guided_attn: 2
      modules_applied_guided_attn:
      - encoder-decoder
      guided_attn_loss_lambda: 10.0
  pitch_extract: null
  pitch_extract_conf: {}
  pitch_normalize: null
  pitch_normalize_conf: {}
  energy_extract: null
  energy_extract_conf: {}
  energy_normalize: null
  energy_normalize_conf: {}
  required:
  - output_dir
  - token_list
  distributed: true