ESPnet2 pretrained model, kan-bayashi/jsut_tts_train_jets_raw_phn_jaconv_pyopenjtalk_prosody_train.total_count.ave_5best, fs=22050, lang=jp

This model was trained by kan-bayashi using jsut/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 14fcb2d42b2609f766ffaa7a79e9c921cd8398d9
  pip install -e .
  cd egs2/jsut/tts1
  # Download the model file here
  ./run.sh --skip_data_prep false --skip_train true --download_model kan-bayashi/jsut_tts_train_jets_raw_phn_jaconv_pyopenjtalk_prosody_train.total_count.ave_5best
  

• Config

  config: conf/tuning/train_jets.yaml
  print_config: false
  log_level: INFO
  dry_run: false
  iterator_type: sequence
  output_dir: exp/tts_train_jets_raw_phn_jaconv_pyopenjtalk_prosody
  ngpu: 1
  seed: 777
  num_workers: 4
  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: 46054
  dist_launcher: null
  multiprocessing_distributed: true
  unused_parameters: true
  sharded_ddp: false
  cudnn_enabled: true
  cudnn_benchmark: false
  cudnn_deterministic: false
  collect_stats: false
  write_collected_feats: false
  max_epoch: 1000
  patience: null
  val_scheduler_criterion:
  - valid
  - loss
  early_stopping_criterion:
  - valid
  - loss
  - min
  best_model_criterion:
  -   - valid
      - text2mel_loss
      - min
  -   - train
      - text2mel_loss
      - min
  -   - train
      - total_count
      - max
  keep_nbest_models: 5
  nbest_averaging_interval: 0
  grad_clip: -1
  grad_clip_type: 2.0
  grad_noise: false
  accum_grad: 1
  no_forward_run: false
  resume: true
  train_dtype: float32
  use_amp: false
  log_interval: 50
  use_matplotlib: true
  use_tensorboard: true
  create_graph_in_tensorboard: false
  use_wandb: false
  wandb_project: null
  wandb_id: null
  wandb_entity: null
  wandb_name: null
  wandb_model_log_interval: -1
  detect_anomaly: false
  pretrain_path: null
  init_param: []
  ignore_init_mismatch: false
  freeze_param: []
  num_iters_per_epoch: 1000
  batch_size: 20
  valid_batch_size: null
  batch_bins: 3000000
  valid_batch_bins: null
  train_shape_file:
  - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/text_shape.phn
  - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/speech_shape
  valid_shape_file:
  - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/valid/text_shape.phn
  - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/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/22k/raw/tr_no_dev/text
      - text
      - text
  -   - dump/22k/raw/tr_no_dev/wav.scp
      - speech
      - sound
  -   - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/collect_feats/pitch.scp
      - pitch
      - npy
  -   - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/collect_feats/energy.scp
      - energy
      - npy
  valid_data_path_and_name_and_type:
  -   - dump/22k/raw/dev/text
      - text
      - text
  -   - dump/22k/raw/dev/wav.scp
      - speech
      - sound
  -   - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/valid/collect_feats/pitch.scp
      - pitch
      - npy
  -   - exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/valid/collect_feats/energy.scp
      - energy
      - npy
  allow_variable_data_keys: false
  max_cache_size: 0.0
  max_cache_fd: 32
  valid_max_cache_size: null
  optim: adamw
  optim_conf:
      lr: 0.0002
      betas:
      - 0.8
      - 0.99
      eps: 1.0e-09
      weight_decay: 0.0
  scheduler: exponentiallr
  scheduler_conf:
      gamma: 0.999875
  optim2: adamw
  optim2_conf:
      lr: 0.0002
      betas:
      - 0.8
      - 0.99
      eps: 1.0e-09
      weight_decay: 0.0
  scheduler2: exponentiallr
  scheduler2_conf:
      gamma: 0.999875
  generator_first: true
  token_list:
  - 
  - 
  - a
  - o
  - i
  - '['
  - '#'
  - u
  - ']'
  - e
  - k
  - n
  - t
  - r
  - s
  - N
  - m
  - _
  - sh
  - d
  - g
  - ^
  - $
  - w
  - cl
  - h
  - y
  - b
  - j
  - ts
  - ch
  - z
  - p
  - f
  - ky
  - ry
  - gy
  - hy
  - ny
  - by
  - my
  - py
  - v
  - dy
  - '?'
  - ty
  - 
  odim: null
  model_conf: {}
  use_preprocessor: true
  token_type: phn
  bpemodel: null
  non_linguistic_symbols: null
  cleaner: jaconv
  g2p: pyopenjtalk_prosody
  feats_extract: fbank
  feats_extract_conf:
      n_fft: 1024
      hop_length: 256
      win_length: null
      fs: 22050
      fmin: 80
      fmax: 7600
      n_mels: 80
  normalize: global_mvn
  normalize_conf:
      stats_file: exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/feats_stats.npz
  tts: jets
  tts_conf:
      generator_type: jets_generator
      generator_params:
          adim: 256
          aheads: 2
          elayers: 4
          eunits: 1024
          dlayers: 4
          dunits: 1024
          positionwise_layer_type: conv1d
          positionwise_conv_kernel_size: 3
          duration_predictor_layers: 2
          duration_predictor_chans: 256
          duration_predictor_kernel_size: 3
          use_masking: true
          encoder_normalize_before: true
          decoder_normalize_before: true
          encoder_type: transformer
          decoder_type: transformer
          conformer_rel_pos_type: latest
          conformer_pos_enc_layer_type: rel_pos
          conformer_self_attn_layer_type: rel_selfattn
          conformer_activation_type: swish
          use_macaron_style_in_conformer: true
          use_cnn_in_conformer: true
          conformer_enc_kernel_size: 7
          conformer_dec_kernel_size: 31
          init_type: xavier_uniform
          transformer_enc_dropout_rate: 0.2
          transformer_enc_positional_dropout_rate: 0.2
          transformer_enc_attn_dropout_rate: 0.2
          transformer_dec_dropout_rate: 0.2
          transformer_dec_positional_dropout_rate: 0.2
          transformer_dec_attn_dropout_rate: 0.2
          pitch_predictor_layers: 5
          pitch_predictor_chans: 256
          pitch_predictor_kernel_size: 5
          pitch_predictor_dropout: 0.5
          pitch_embed_kernel_size: 1
          pitch_embed_dropout: 0.0
          stop_gradient_from_pitch_predictor: true
          energy_predictor_layers: 2
          energy_predictor_chans: 256
          energy_predictor_kernel_size: 3
          energy_predictor_dropout: 0.5
          energy_embed_kernel_size: 1
          energy_embed_dropout: 0.0
          stop_gradient_from_energy_predictor: false
          generator_out_channels: 1
          generator_channels: 512
          generator_global_channels: -1
          generator_kernel_size: 7
          generator_upsample_scales:
          - 8
          - 8
          - 2
          - 2
          generator_upsample_kernel_sizes:
          - 16
          - 16
          - 4
          - 4
          generator_resblock_kernel_sizes:
          - 3
          - 7
          - 11
          generator_resblock_dilations:
          -   - 1
              - 3
              - 5
          -   - 1
              - 3
              - 5
          -   - 1
              - 3
              - 5
          generator_use_additional_convs: true
          generator_bias: true
          generator_nonlinear_activation: LeakyReLU
          generator_nonlinear_activation_params:
              negative_slope: 0.1
          generator_use_weight_norm: true
          segment_size: 64
          idim: 47
          odim: 80
      discriminator_type: hifigan_multi_scale_multi_period_discriminator
      discriminator_params:
          scales: 1
          scale_downsample_pooling: AvgPool1d
          scale_downsample_pooling_params:
              kernel_size: 4
              stride: 2
              padding: 2
          scale_discriminator_params:
              in_channels: 1
              out_channels: 1
              kernel_sizes:
              - 15
              - 41
              - 5
              - 3
              channels: 128
              max_downsample_channels: 1024
              max_groups: 16
              bias: true
              downsample_scales:
              - 2
              - 2
              - 4
              - 4
              - 1
              nonlinear_activation: LeakyReLU
              nonlinear_activation_params:
                  negative_slope: 0.1
              use_weight_norm: true
              use_spectral_norm: false
          follow_official_norm: false
          periods:
          - 2
          - 3
          - 5
          - 7
          - 11
          period_discriminator_params:
              in_channels: 1
              out_channels: 1
              kernel_sizes:
              - 5
              - 3
              channels: 32
              downsample_scales:
              - 3
              - 3
              - 3
              - 3
              - 1
              max_downsample_channels: 1024
              bias: true
              nonlinear_activation: LeakyReLU
              nonlinear_activation_params:
                  negative_slope: 0.1
              use_weight_norm: true
              use_spectral_norm: false
      generator_adv_loss_params:
          average_by_discriminators: false
          loss_type: mse
      discriminator_adv_loss_params:
          average_by_discriminators: false
          loss_type: mse
      feat_match_loss_params:
          average_by_discriminators: false
          average_by_layers: false
          include_final_outputs: true
      mel_loss_params:
          fs: 22050
          n_fft: 1024
          hop_length: 256
          win_length: null
          window: hann
          n_mels: 80
          fmin: 0
          fmax: null
          log_base: null
      lambda_adv: 1.0
      lambda_mel: 45.0
      lambda_feat_match: 2.0
      lambda_var: 1.0
      lambda_align: 2.0
      sampling_rate: 22050
      cache_generator_outputs: true
  pitch_extract: dio
  pitch_extract_conf:
      reduction_factor: 1
      use_token_averaged_f0: false
      fs: 22050
      n_fft: 1024
      hop_length: 256
      f0max: 400
      f0min: 80
  pitch_normalize: global_mvn
  pitch_normalize_conf:
      stats_file: exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/pitch_stats.npz
  energy_extract: energy
  energy_extract_conf:
      reduction_factor: 1
      use_token_averaged_energy: false
      fs: 22050
      n_fft: 1024
      hop_length: 256
      win_length: null
  energy_normalize: global_mvn
  energy_normalize_conf:
      stats_file: exp/tts_stats_raw_22.05khz_phn_jaconv_pyopenjtalk_prosody_jets/train/energy_stats.npz
  required:
  - output_dir
  - token_list
  version: '202205'
  distributed: true