Initial commit

README.md

@@ -0,0 +1,51 @@
+---
+tags:
+- espnet
+- audio
+- text-to-speech
+language: ko
+datasets:
+- Jaewook
+license: cc-by-4.0
+---
+
+## ESPnet2 TTS model
+
+### yesyesjaewook/jets-jaewook-ko
+
+This model was trained by yesyesjaewook using jaewook recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Citing ESPnet
+
+```BibTex
+@inproceedings{watanabe2018espnet,
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  title={{ESPnet}: End-to-End Speech Processing Toolkit},
+  year={2018},
+  booktitle={Proceedings of Interspeech},
+  pages={2207--2211},
+  doi={10.21437/Interspeech.2018-1456},
+  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
+}
+@inproceedings{hayashi2020espnet,
+  title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
+  author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
+  booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={7654--7658},
+  year={2020},
+  organization={IEEE}
+}
+```
+
+or arXiv:
+
+```bibtex
+@misc{watanabe2018espnet,
+  title={ESPnet: End-to-End Speech Processing Toolkit},
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  year={2018},
+  eprint={1804.00015},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL}
+}
+```

experiments/tts_jaewook/config.yaml

@@ -0,0 +1,420 @@
+config: conf/fine_tune_jets_multi_lang.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: experiments/tts_jaewook
+ngpu: 1
+seed: 777
+num_workers: 8
+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
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: false
+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
+    - text2mel_loss
+    - min
+-   - train
+    - text2mel_loss
+    - min
+-   - train
+    - total_count
+    - max
+keep_nbest_models: 100
+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: true
+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:
+- tts.generator.lid_emb
+num_iters_per_epoch: 1000
+batch_size: 20
+valid_batch_size: null
+batch_bins: 3500000
+valid_batch_bins: null
+train_shape_file:
+- experiments/tts_stats_raw_phn_none/train/text_shape.phn
+- experiments/tts_stats_raw_phn_none/train/speech_shape
+valid_shape_file:
+- experiments/tts_stats_raw_phn_none/valid/text_shape.phn
+- experiments/tts_stats_raw_phn_none/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
+chunk_excluded_key_prefixes: []
+train_data_path_and_name_and_type:
+-   - dumps/raw/train_phn/text
+    - text
+    - text
+-   - dumps/raw/train_phn/wav.scp
+    - speech
+    - sound
+-   - dumps/raw/train_phn/utt2lid
+    - lids
+    - text_int
+valid_data_path_and_name_and_type:
+-   - dumps/raw/dev_phn/text
+    - text
+    - text
+-   - dumps/raw/dev_phn/wav.scp
+    - speech
+    - sound
+-   - dumps/raw/dev_phn/utt2lid
+    - lids
+    - text_int
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adamw
+optim_conf:
+    lr: 1.0e-05
+    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: 1.0e-05
+    betas:
+    - 0.8
+    - 0.99
+    eps: 1.0e-09
+    weight_decay: 0.0
+scheduler2: exponentiallr
+scheduler2_conf:
+    gamma: 0.999875
+generator_first: true
+token_list:
+- <blank>
+- <unk>
+- <space>
+- ᅡ
+- ᅵ
+- ᅳ
+- ᄋ
+- ᄀ
+- ᄂ
+- ᅥ
+- ᄅ
+- ᆫ
+- ᅩ
+- ᄃ
+- ᆯ
+- ᄉ
+- ᄆ
+- ᄌ
+- ᅮ
+- .
+- ᄒ
+- ᆮ
+- ᆼ
+- ᅧ
+- ᅢ
+- ᄇ
+- ᅦ
+- ᄊ
+- ᄄ
+- ᆷ
+- ᄁ
+- ᄎ
+- ᄏ
+- ᆨ
+- ᄑ
+- ᄐ
+- ᅪ
+- ᅭ
+- ᅴ
+- ᄍ
+- ᆸ
+- ᅣ
+- ᅬ
+- ᅱ
+- ᄈ
+- ᅯ
+- '?'
+- ᅨ
+- ','
+- ᅲ
+- ᅫ
+- '!'
+- ᅤ
+- ᅰ
+- '~'
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: korean_cleaner
+g2p: g2pk_explicit_space
+feats_extract: fbank
+feats_extract_conf:
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+    fs: 22050
+    fmin: 0
+    fmax: null
+    n_mels: 80
+normalize: global_mvn
+normalize_conf:
+    stats_file: experiments/tts_stats_raw_phn_none/train/feats_stats.npz
+tts: jets
+tts_conf:
+    generator_type: jets_generator
+    generator_params:
+        langs: 96
+        adim: 256
+        aheads: 2
+        elayers: 4
+        eunits: 1024
+        dlayers: 4
+        dunits: 1024
+        positionwise_layer_type: conv1d
+        positionwise_conv_kernel_size: 3
+        duration_predictor_layers: 2
+        duration_predictor_chans: 256
+        duration_predictor_kernel_size: 3
+        use_masking: true
+        encoder_normalize_before: true
+        decoder_normalize_before: true
+        encoder_type: transformer
+        decoder_type: transformer
+        conformer_rel_pos_type: latest
+        conformer_pos_enc_layer_type: rel_pos
+        conformer_self_attn_layer_type: rel_selfattn
+        conformer_activation_type: swish
+        use_macaron_style_in_conformer: true
+        use_cnn_in_conformer: true
+        conformer_enc_kernel_size: 7
+        conformer_dec_kernel_size: 31
+        init_type: xavier_uniform
+        transformer_enc_dropout_rate: 0.2
+        transformer_enc_positional_dropout_rate: 0.2
+        transformer_enc_attn_dropout_rate: 0.2
+        transformer_dec_dropout_rate: 0.2
+        transformer_dec_positional_dropout_rate: 0.2
+        transformer_dec_attn_dropout_rate: 0.2
+        pitch_predictor_layers: 5
+        pitch_predictor_chans: 256
+        pitch_predictor_kernel_size: 5
+        pitch_predictor_dropout: 0.5
+        pitch_embed_kernel_size: 1
+        pitch_embed_dropout: 0.0
+        stop_gradient_from_pitch_predictor: true
+        energy_predictor_layers: 2
+        energy_predictor_chans: 256
+        energy_predictor_kernel_size: 3
+        energy_predictor_dropout: 0.5
+        energy_embed_kernel_size: 1
+        energy_embed_dropout: 0.0
+        stop_gradient_from_energy_predictor: false
+        generator_out_channels: 1
+        generator_channels: 512
+        generator_global_channels: -1
+        generator_kernel_size: 7
+        generator_upsample_scales:
+        - 8
+        - 8
+        - 2
+        - 2
+        generator_upsample_kernel_sizes:
+        - 16
+        - 16
+        - 4
+        - 4
+        generator_resblock_kernel_sizes:
+        - 3
+        - 7
+        - 11
+        generator_resblock_dilations:
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        generator_use_additional_convs: true
+        generator_bias: true
+        generator_nonlinear_activation: LeakyReLU
+        generator_nonlinear_activation_params:
+            negative_slope: 0.1
+        generator_use_weight_norm: true
+        segment_size: 64
+        idim: 56
+        odim: 80
+    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_var: 1.0
+    lambda_align: 2.0
+    sampling_rate: 22050
+    cache_generator_outputs: true
+pitch_extract: dio
+pitch_extract_conf:
+    reduction_factor: 1
+    use_token_averaged_f0: false
+    fs: 22050
+    n_fft: 1024
+    hop_length: 256
+    f0max: 400
+    f0min: 80
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+    stats_file: experiments/tts_stats_raw_phn_none/train/pitch_stats.npz
+energy_extract: energy
+energy_extract_conf:
+    reduction_factor: 1
+    use_token_averaged_energy: false
+    fs: 22050
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+energy_normalize: global_mvn
+energy_normalize_conf:
+    stats_file: experiments/tts_stats_raw_phn_none/train/energy_stats.npz
+required:
+- output_dir
+- token_list
+version: '202301'
+distributed: false

experiments/tts_jaewook/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffec6be5944f06e945f461f2cbc0ac7358a31bcd2718412a3f01d984728fc78b
+size 333767147

experiments/tts_stats_raw_phn_none/train/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae615a5bf81d1ccdbd7577dea026a5e6fcdef3f67cc390c6cf2896979054b09e
+size 770

experiments/tts_stats_raw_phn_none/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc6e274870e5dc3fd137ab378d707332b8429fd4dc09a14ee9e7f88dd5f3584
+size 1402

experiments/tts_stats_raw_phn_none/train/pitch_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a62c752d615f82e2f0182696c4c22c9f1a57226035e06ada5490f2a3c0d4ef
+size 770

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202301'
+files:
+  model_file: experiments/tts_jaewook/model.pth
+python: 3.10.9 (main, Dec 29 2022, 07:07:21) [GCC 11.3.0]
+timestamp: 1680614714.734043
+torch: 1.13.1+cu117
+yaml_files:
+  train_config: experiments/tts_jaewook/config.yaml