add files

README.md

@@ -1,3 +1,39 @@
 ---
+tags:
+- espnet
+- audio
+- audio-to-audio
+- vocoder
+language: 
+- multilingual
+datasets:
+- libritts
+- csj
+- css10
+- aishell3
+- jvs
+- jsss
+- jsut
 license: cc-by-4.0
 ---
+
+## Vocoder model - FastDiff
+
+**No support given.**
+
+### Details
+
+```
+num_iters_per_epoch: 250
+max_epoch: 1000
+batch_size: 64
+vocoder_conf:
+    audio_channels: 1
+    inner_channels: 32
+    cond_channels: 80
+    upsample_ratios:
+    - 5
+    - 5
+    - 4
+    - 3
+```

exp/tts_vocoder_fastdiff/config.yaml

@@ -0,0 +1,176 @@
+config: conf/tuning/fastdiff.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_vocoder_fastdiff
+ngpu: 1
+seed: 0
+num_workers: 6
+num_att_plot: 3
+num_valid_artifacts: 5
+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
+growth_interval: 0
+min_grad_scale: -1
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 1000
+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: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+detect_anomaly: false
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 250
+batch_size: 64
+valid_batch_size: null
+valid_num_batches: 100
+batch_bins: 1000000
+valid_batch_bins: 3000000
+train_shape_file:
+- exp/voc_stats_raw/train/text_shape.char
+- exp/voc_stats_raw/train/speech_shape
+valid_shape_file:
+- exp/voc_stats_raw/valid/text_shape.char
+- exp/voc_stats_raw/valid/speech_shape
+batch_type: unsorted
+valid_batch_type: numel
+fold_length:
+- 150
+- 240000
+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_no_dev/text
+    - text
+    - text
+-   - dump/raw/train_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:
+    - 0.9
+    - 0.98
+    eps: 1.0e-09
+scheduler: null
+scheduler_conf: {}
+collate_fn_conf: {}
+token_list: dump/token_list/char/tokens.txt
+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: 2048
+    hop_length: 300
+    win_length: 1200
+    fs: 24000
+    fmin: 80
+    fmax: 7600
+    n_mels: 80
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/voc_stats_raw/train/feats_stats.npz
+vocoder: fastdiff
+vocoder_conf:
+    audio_channels: 1
+    inner_channels: 32
+    cond_channels: 80
+    upsample_ratios:
+    - 5
+    - 5
+    - 4
+    - 3
+    lvc_layers_each_block: 4
+    lvc_kernel_size: 3
+    kpnet_hidden_channels: 64
+    kpnet_conv_size: 3
+    dropout: 0.05
+    diffusion_step_embed_dim_in: 128
+    diffusion_step_embed_dim_mid: 512
+    diffusion_step_embed_dim_out: 512
+    use_weight_norm: true
+    mel_loss_params:
+        fs: 24000
+        fft_size: 2048
+        hop_size: 300
+        win_length: 1200
+        window: hann
+        num_mels: 80
+        fmin: 0
+        fmax: 12000
+        log_base: null
+pitch_extract: null
+pitch_extract_conf: {}
+energy_extract: null
+energy_extract_conf: {}
+pitch_normalize: null
+pitch_normalize_conf: {}
+energy_normalize: null
+energy_normalize_conf: {}
+required:
+- output_dir
+version: '202207'
+distributed: false

exp/tts_vocoder_fastdiff/train.loss.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730b9c876a8e4ef6a41a39437a0dd604c91974816921274986be788badfcf0b9
+size 81577071

exp/voc_stats_raw/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88a8e0ee800d551db34b05e14c39f627ee77200a44977678ad57d30f22df68a
+size 1402

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202207'
+files:
+  model_file: exp/tts_vocoder_fastdiff/train.loss.ave_5best.pth
+python: "3.9.13 (main, Aug 25 2022, 23:26:10) \n[GCC 11.2.0]"
+timestamp: 1673910959.463416
+torch: 1.12.1
+yaml_files:
+  train_config: exp/tts_vocoder_fastdiff/config.yaml