Add tts model

tts_model/exp/tts_train_vits_raw_phn_tacotron_g2p_en_no_space/config.yaml

@@ -0,0 +1,385 @@
+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_tacotron_g2p_en_no_space
+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: 36133
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+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_tacotron_g2p_en_no_space/train/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en_no_space/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en_no_space/valid/text_shape.phn
+- exp/tts_stats_raw_linear_spectrogram_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
+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:
+- <blank>
+- <unk>
+- 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
+- ..
+- <sos/eos>
+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: 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: 78
+        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

tts_model/exp/tts_train_vits_raw_phn_tacotron_g2p_en_no_space/train.total_count.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84752ef48430c0cad8fc182d6255670bdaff38903e366c136b7aa8c63b64a97a
+size 372559183

tts_model/meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.3a1
+files:
+  model_file: exp/tts_train_vits_raw_phn_tacotron_g2p_en_no_space/train.total_count.ave_10best.pth
+python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
+timestamp: 1630751435.588649
+torch: 1.7.1
+yaml_files:
+  train_config: exp/tts_train_vits_raw_phn_tacotron_g2p_en_no_space/config.yaml