add ttts

exp/tts_train_transformer_raw_char/config.yaml

@@ -0,0 +1,306 @@
+config: conf/tuning/train_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_train_transformer_raw_char
+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
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 3000
+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
+nbest_averaging_interval: 0
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 2
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+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: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 640000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_char/train/text_shape.char
+- exp/tts_stats_raw_char/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_char/valid/text_shape.char
+- exp/tts_stats_raw_char/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/train/text
+    - text
+    - text
+-   - dump/raw/train/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: adam
+optim_conf:
+    lr: 1.0
+scheduler: noamlr
+scheduler_conf:
+    model_size: 512
+    warmup_steps: 8000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- ा
+- ्
+- र
+- े
+- त
+- य
+- ी
+- क
+- ल
+- न
+- स
+- ि
+- व
+- ं
+- म
+- च
+- ह
+- प
+- ो
+- ण
+- द
+- ज
+- ु
+- आ
+- ग
+- ट
+- श
+- ब
+- ड
+- ','
+- अ
+- ू
+- ध
+- ळ
+- ष
+- .
+- ख
+- भ
+- फ
+- थ
+- ठ
+- घ
+- ॉ
+- ए
+- झ
+- उ
+- ॅ
+- इ
+- ई
+- ढ
+- ै
+- ँ
+- ृ
+- ऊ
+- ौ
+- १
+- ऱ
+- ''''
+- ओ
+- ०
+- २
+- ऑ
+- छ
+- ञ
+- य़
+- ३
+- ५
+- ४
+- ९
+- ६
+- ८
+- '"'
+- औ
+- ७
+- ऐ
+- '?'
+- ऍ
+- ॥
+- फ़
+- ऋ
+- ः
+- ़
+- ।
+- '-'
+- ड़
+- ङ
+- ऽ
+- ':'
+- ज़
+- ॄ
+- क़
+- ॊ
+- ‘
+- ’
+- ढ़
+- /
+- ऎ
+- ॆ
+- ॐ
+- ग़
+- '!'
+- ॠ
+- ऩ
+- ख़
+- ऒ
+- o
+- ऴ
+- (
+- )
+- ;
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+feats_extract: fbank
+feats_extract_conf:
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+    fs: 22050
+    fmin: 0
+    fmax: 8000
+    n_mels: 80
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_char/train/feats_stats.npz
+tts: transformer
+tts_conf:
+    embed_dim: 0
+    eprenet_conv_layers: 0
+    eprenet_conv_filts: 0
+    eprenet_conv_chans: 0
+    dprenet_layers: 2
+    dprenet_units: 256
+    adim: 512
+    aheads: 8
+    elayers: 6
+    eunits: 1024
+    dlayers: 6
+    dunits: 1024
+    positionwise_layer_type: conv1d
+    positionwise_conv_kernel_size: 1
+    postnet_layers: 5
+    postnet_filts: 5
+    postnet_chans: 256
+    use_masking: true
+    bce_pos_weight: 5.0
+    use_scaled_pos_enc: true
+    encoder_normalize_before: true
+    decoder_normalize_before: true
+    reduction_factor: 1
+    init_type: xavier_uniform
+    init_enc_alpha: 1.0
+    init_dec_alpha: 1.0
+    eprenet_dropout_rate: 0.0
+    dprenet_dropout_rate: 0.5
+    postnet_dropout_rate: 0.5
+    transformer_enc_dropout_rate: 0.1
+    transformer_enc_positional_dropout_rate: 0.1
+    transformer_enc_attn_dropout_rate: 0.1
+    transformer_dec_dropout_rate: 0.1
+    transformer_dec_positional_dropout_rate: 0.1
+    transformer_dec_attn_dropout_rate: 0.1
+    transformer_enc_dec_attn_dropout_rate: 0.1
+    use_guided_attn_loss: true
+    num_heads_applied_guided_attn: 2
+    num_layers_applied_guided_attn: 2
+    modules_applied_guided_attn:
+    - encoder-decoder
+    guided_attn_loss_sigma: 0.4
+    guided_attn_loss_lambda: 10.0
+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: 0.10.7a1
+distributed: false

exp/tts_train_transformer_raw_char/valid.loss.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936c11683afdc4de0992d22d11aba1c08b6c72d72d08b0283de7befc5a63119e
+size 132498531