Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published September 10, 2021 | Version v1
Other Open

ESPnet2 pretrained model, kan-bayashi/csmsc_tts_train_vits_raw_phn_pypinyin_g2p_phone_train.total_count.ave, fs=22050, lang=zh

Creators

Description

This model was trained by kan-bayashi using csmsc/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 628b46282537ce532d613d6bafb75e826e8455de
    pip install -e .
    cd egs2/csmsc/tts1
    # Download the model file here
    ./run.sh --skip_data_prep false --skip_train true --download_model kan-bayashi/csmsc_tts_train_vits_raw_phn_pypinyin_g2p_phone_train.total_count.ave
    
  • Config
    config: ./conf/tuning/train_vits.yaml
    print_config: false
    log_level: INFO
    dry_run: false
    iterator_type: sequence
    output_dir: exp/tts_train_vits_raw_phn_pypinyin_g2p_phone
    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: 41492
    dist_launcher: null
    multiprocessing_distributed: true
    unused_parameters: true
    sharded_ddp: false
    cudnn_enabled: true
    cudnn_benchmark: true
    cudnn_deterministic: false
    collect_stats: false
    write_collected_feats: false
    max_epoch: 2000
    patience: null
    val_scheduler_criterion:
    - valid
    - loss
    early_stopping_criterion:
    - valid
    - loss
    - min
    best_model_criterion:
    -   - train
        - total_count
        - max
    keep_nbest_models: 10
    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_tensorboard: true
    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: 500
    batch_size: 20
    valid_batch_size: null
    batch_bins: 5000000
    valid_batch_bins: null
    train_shape_file:
    - exp/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/train/text_shape.phn
    - exp/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/train/speech_shape
    valid_shape_file:
    - exp/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/valid/text_shape.phn
    - exp/tts_stats_raw_linear_spectrogram_phn_pypinyin_g2p_phone/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
    valid_data_path_and_name_and_type:
    -   - dump/22k/raw/dev/text
        - text
        - text
    -   - dump/22k/raw/dev/wav.scp
        - speech
        - sound
    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: false
    token_list:
    - 
    - 
    - d
    - sh
    - j
    - l
    - 。
    - zh
    - ,
    - i4
    - x
    - h
    - b
    - e
    - g
    - t
    - m
    - z
    - q
    - i1
    - i3
    - ch
    - u4
    - n
    - f
    - i2
    - r
    - k
    - s
    - e4
    - ai4
    - a1
    - c
    - p
    - ian4
    - uo3
    - ao3
    - ai2
    - ao4
    - an4
    - u3
    - ong1
    - ing2
    - en2
    - u2
    - e2
    - ui4
    - ian2
    - iou3
    - ang4
    - u1
    - iao4
    - uo4
    - eng2
    - a4
    - in1
    - ang1
    - eng1
    - ou3
    - ian1
    - ou4
    - ing1
    - uo1
    - an1
    - ian3
    - ie3
    - a3
    - an3
    - ing4
    - an2
    - ü4
    - iao3
    - ei4
    - ong2
    - en1
    - uei4
    - üan2
    - ang2
    - ang3
    - iu4
    - iang4
    - ai3
    - ao1
    - ou1
    - eng4
    - iang3
    - en3
    - ai1
    - ong4
    - ie4
    - e3
    - ia1
    - uo2
    - ia4
    - ü3
    - uan1
    - er2
    - ei3
    - ei2
    - iang1
    - ing3
    - en4
    - ü2
    - uan3
    - e1
    - in2
    - iao1
    - i
    - in4
    - ie1
    - ong3
    - iang2
    - ie2
    - uan4
    - a2
    - ui3
    - eng3
    - uan2
    - üe4
    - uai4
    - ou2
    - ?
    - üe2
    - in3
    - uang3
    - uang1
    - iu2
    - en
    - a
    - ao2
    - ua4
    - un1
    - ui1
    - uei2
    - iong4
    - uang2
    - v3
    - ui2
    - iao2
    - uang4
    - ü1
    - ei1
    - o2
    - er4
    - iou2
    - iou4
    - !
    - ua1
    - üan4
    - iu3
    - un4
    - üan3
    - ün4
    - uen2
    - iu1
    - un3
    - uen4
    - un2
    - er3
    - ün1
    - ün2
    - o4
    - o1
    - ua2
    - uei1
    - uei3
    - ia3
    - iong3
    - ua3
    - ia
    - v4
    - üe1
    - üan1
    - iong1
    - ia2
    - uai1
    - iong2
    - iou1
    - uai3
    - üe3
    - uen1
    - uen3
    - uai2
    - o3
    - er
    - ve4
    - ou
    - io1
    - ün3
    - ueng1
    - v2
    - uo
    - ueng4
    - o
    - ua
    - ei
    - '2'
    - ueng3
    - ang
    - P
    - B
    - 
    odim: null
    model_conf: {}
    use_preprocessor: true
    token_type: phn
    bpemodel: null
    non_linguistic_symbols: null
    cleaner: null
    g2p: pypinyin_g2p_phone
    feats_extract: linear_spectrogram
    feats_extract_conf:
        n_fft: 1024
        hop_length: 256
        win_length: null
    normalize: null
    normalize_conf: {}
    tts: vits
    tts_conf:
        generator_type: vits_generator
        generator_params:
            hidden_channels: 192
            spks: -1
            global_channels: -1
            segment_size: 32
            text_encoder_attention_heads: 2
            text_encoder_ffn_expand: 4
            text_encoder_blocks: 6
            text_encoder_positionwise_layer_type: conv1d
            text_encoder_positionwise_conv_kernel_size: 3
            text_encoder_positional_encoding_layer_type: rel_pos
            text_encoder_self_attention_layer_type: rel_selfattn
            text_encoder_activation_type: swish
            text_encoder_normalize_before: true
            text_encoder_dropout_rate: 0.1
            text_encoder_positional_dropout_rate: 0.0
            text_encoder_attention_dropout_rate: 0.1
            use_macaron_style_in_text_encoder: true
            use_conformer_conv_in_text_encoder: false
            text_encoder_conformer_kernel_size: -1
            decoder_kernel_size: 7
            decoder_channels: 512
            decoder_upsample_scales:
            - 8
            - 8
            - 2
            - 2
            decoder_upsample_kernel_sizes:
            - 16
            - 16
            - 4
            - 4
            decoder_resblock_kernel_sizes:
            - 3
            - 7
            - 11
            decoder_resblock_dilations:
            -   - 1
                - 3
                - 5
            -   - 1
                - 3
                - 5
            -   - 1
                - 3
                - 5
            use_weight_norm_in_decoder: true
            posterior_encoder_kernel_size: 5
            posterior_encoder_layers: 16
            posterior_encoder_stacks: 1
            posterior_encoder_base_dilation: 1
            posterior_encoder_dropout_rate: 0.0
            use_weight_norm_in_posterior_encoder: true
            flow_flows: 4
            flow_kernel_size: 5
            flow_base_dilation: 1
            flow_layers: 4
            flow_dropout_rate: 0.0
            use_weight_norm_in_flow: true
            use_only_mean_in_flow: true
            stochastic_duration_predictor_kernel_size: 3
            stochastic_duration_predictor_dropout_rate: 0.5
            stochastic_duration_predictor_flows: 4
            stochastic_duration_predictor_dds_conv_layers: 3
            vocabs: 202
            aux_channels: 513
        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_dur: 1.0
        lambda_kl: 1.0
        sampling_rate: 22050
        cache_generator_outputs: true
    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
    version: 0.10.3a1
    distributed: true

Files

tts_train_vits_raw_phn_pypinyin_g2p_phone_train.total_count.ave.zip

Files (373.6 MB)

Additional details

Related works

Is supplement to
https://github.com/espnet/espnet (URL)