Other Open Access

ESPnet2 pretrained model, kan-bayashi/ljspeech_tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.best, fs=22050, lang=en

kan-bayashi

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 51d986f1b270b2f3da23fd89376219316a0c8a73
    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_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.best
    
  • Config
    config: conf/tuning/train_tacotron2.yaml
    print_config: false
    log_level: INFO
    dry_run: false
    iterator_type: sequence
    output_dir: exp/tts_train_tacotron2_raw
    ngpu: 1
    seed: 0
    num_workers: 1
    num_att_plot: 3
    dist_backend: nccl
    dist_init_method: env://
    dist_world_size: null
    dist_rank: null
    local_rank: 0
    dist_master_addr: null
    dist_master_port: null
    dist_launcher: null
    multiprocessing_distributed: false
    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_noise: false
    accum_grad: 1
    no_forward_run: false
    resume: true
    train_dtype: float32
    log_interval: null
    pretrain_path: []
    pretrain_key: []
    num_iters_per_epoch: null
    batch_size: 20
    valid_batch_size: null
    batch_bins: 5120000
    valid_batch_bins: null
    train_shape_file:
    - exp/tts_stats_raw/train/text_shape.phn
    - exp/tts_stats_raw/train/speech_shape
    valid_shape_file:
    - exp/tts_stats_raw/valid/text_shape.phn
    - exp/tts_stats_raw/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: 0.001
        eps: 1.0e-06
        weight_decay: 0.0
    scheduler: null
    scheduler_conf: {}
    token_list:
    - 
    - 
    - ..
    - OY0
    - UH0
    - AW0
    - '!'
    - OY2
    - '?'
    - UH2
    - ER2
    - ''''
    - AA0
    - IY2
    - AW2
    - AY0
    - AH2
    - UW2
    - AE0
    - OW2
    - ZH
    - AO2
    - EY0
    - OY1
    - EH0
    - UW0
    - AA2
    - AY2
    - AE2
    - IH2
    - AO0
    - EY2
    - OW0
    - EH2
    - UH1
    - TH
    - AW1
    - Y
    - JH
    - CH
    - ER1
    - G
    - NG
    - SH
    - OW1
    - .
    - AY1
    - EY1
    - AO1
    - IY0
    - UW1
    - IY1
    - HH
    - B
    - AA1
    - ','
    - F
    - ER0
    - V
    - AH1
    - AE1
    - P
    - W
    - EH1
    - M
    - IH0
    - IH1
    - Z
    - K
    - DH
    - L
    - R
    - S
    - D
    - T
    - N
    - AH0
    - 
    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: tacotron2
    tts_conf:
        embed_dim: 512
        elayers: 1
        eunits: 512
        econv_layers: 3
        econv_chans: 512
        econv_filts: 5
        atype: location
        adim: 512
        aconv_chans: 32
        aconv_filts: 15
        cumulate_att_w: true
        dlayers: 2
        dunits: 1024
        prenet_layers: 2
        prenet_units: 256
        postnet_layers: 5
        postnet_chans: 512
        postnet_filts: 5
        output_activation: null
        use_batch_norm: true
        use_concate: true
        use_residual: false
        dropout_rate: 0.5
        zoneout_rate: 0.1
        reduction_factor: 1
        spk_embed_dim: null
        use_masking: true
        bce_pos_weight: 5.0
        use_guided_attn_loss: true
        guided_attn_loss_sigma: 0.4
        guided_attn_loss_lambda: 1.0
    required:
    - output_dir
    - token_list
    distributed: false
Files (106.9 MB)
Name Size
tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.best.zip
md5:e21021e5d3c012056a192525bf2db453
106.9 MB Download
242
2,930
views
downloads
All versions This version
Views 242242
Downloads 2,9302,930
Data volume 313.1 GB313.1 GB
Unique views 227227
Unique downloads 1,7741,774

Share

Cite as