dailytalk_VITS

ESPnet2 TTS model

espnet/dailytalk_VITS

This model was trained by RuiRuihigh using dailytalk recipe in espnet.

Demo: How to use in ESPnet2

Follow the ESPnet installation instructions if you haven't done that already.

cd espnet
git checkout 54754e9a59162bfade5d26534ef203a5c1f131ab
pip install -e .
cd egs2/dailytalk/tts1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/dailytalk_VITS

TTS config

config: conf/train.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: exp/tts_dailytalk_vits
ngpu: 1
seed: 777
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
unused_parameters: true
sharded_ddp: false
use_deepspeed: false
deepspeed_config: null
gradient_as_bucket_view: true
ddp_comm_hook: null
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: false
use_tf32: false
collect_stats: false
write_collected_feats: false
max_epoch: 500
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - 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
wandb_allow_val_change: true
detect_anomaly: false
use_adapter: false
adapter: lora
save_strategy: all
adapter_conf: {}
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: 1500000
valid_batch_bins: null
category_sample_size: 10
upsampling_factor: 0.5
category_upsampling_factor: 0.5
dataset_upsampling_factor: 0.5
dataset_scaling_factor: 1.2
max_batch_size: null
min_batch_size: 1
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
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
chunk_length: 500
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
chunk_excluded_key_prefixes: []
chunk_default_fs: null
chunk_max_abs_length: null
chunk_discard_short_samples: true
train_data_path_and_name_and_type:
-   - dump/raw/tr_no_dev/text
    - text
    - text
-   - dump/raw/tr_no_dev/wav.scp
    - speech
    - sound
-   - dump/raw/tr_no_dev/utt2sid
    - sids
    - text_int
valid_data_path_and_name_and_type:
-   - dump/raw/dev/text
    - text
    - text
-   - dump/raw/dev/wav.scp
    - speech
    - sound
-   - dump/raw/dev/utt2sid
    - sids
    - text_int
multi_task_dataset: false
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
allow_multi_rates: false
valid_max_cache_size: null
exclude_weight_decay: false
exclude_weight_decay_conf: {}
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
skip_discriminator_prob: 0.0
token_list:
-
-
- T
- N
- AH0
- S
- R
- L
- D
- .
- K
- IH1
- UW1
- AY1
- M
- EH1
- AE1
- W
- AH1
- Y
- DH
- IY1
- Z
- AA1
- B
- F
- P
- V
- IH0
- HH
- ','
- OW1
- AO1
- EY1
- IY0
- '?'
- ER0
- NG
- G
- AW1
- UH1
- TH
- SH
- CH
- ER1
- JH
- '!'
- EY2
- IH2
- EH2
- OW0
- OW2
- OY1
- AE2
- UW0
- AY2
- '...'
- AO2
- ZH
- AA2
- AY0
- AH2
- EH0
- UW2
- AE0
- AO0
- ''''
- IY2
- AA0
- UH2
- EY0
- AW2
- AW0
- ER2
- ..
- UH0
- OY0
- OY2
- . ...
-
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:
    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_phn_tacotron_g2p_en_no_space/train/feats_stats.npz
tts: vits
tts_conf:
    generator_type: vits_generator
    generator_params:
        hidden_channels: 192
        spks: 3
        global_channels: 256
        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:
        -