import from zenodo

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- espnet
+- audio
+- text-to-speech
+language: en
+datasets:
+- ljspeech
+license: cc-by-4.0
+---
+## ESPnet2 TTS pretrained model 
+### `kan-bayashi/ljspeech_joint_finetune_conformer_fastspeech2_hifigan`
+♻️ Imported from https://zenodo.org/record/5498896/
+
+This model was trained by kan-bayashi using ljspeech/tts1 recipe in [espnet](https://github.com/espnet/espnet/).
+### Demo: How to use in ESPnet2
+```python
+# coming soon
+```
+### 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 {Enrique Yalta Soplin} 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 Enrique Yalta Soplin 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}
+}
+```

exp/tts_finetune_joint_conformer_fastspeech2_hifigan.v8_raw_phn_tacotron_g2p_en_no_space/config.yaml

@@ -0,0 +1,449 @@
+config: ./conf/tuning/finetune_joint_conformer_fastspeech2_hifigan.v8.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_finetune_joint_conformer_fastspeech2_hifigan.v8_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: 51963
+dist_launcher: null
+multiprocessing_distributed: true
+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: 5
+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: 10
+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:
+- exp/tts_train_conformer_fastspeech2_raw_phn_tacotron_g2p_en_no_space/train.loss.ave_5best.pth:tts:tts.generator.text2mel
+- exp/ljspeech_hifigan.v1/generator.pth::tts.generator.vocoder
+- exp/ljspeech_hifigan.v1/discriminator.pth::tts.discriminator
+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_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/text_shape.phn
+- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/speech_shape
+valid_shape_file:
+- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/valid/text_shape.phn
+- exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/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
+-   - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/tr_no_dev/durations
+    - durations
+    - text_int
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/collect_feats/energy.scp
+    - energy
+    - npy
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/dev/durations
+    - durations
+    - text_int
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/valid/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/valid/collect_feats/energy.scp
+    - energy
+    - npy
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 1.25e-05
+    betas:
+    - 0.5
+    - 0.9
+    weight_decay: 0.0
+scheduler: exponentiallr
+scheduler_conf:
+    gamma: 0.999875
+optim2: adam
+optim2_conf:
+    lr: 1.25e-05
+    betas:
+    - 0.5
+    - 0.9
+    weight_decay: 0.0
+scheduler2: exponentiallr
+scheduler2_conf:
+    gamma: 0.999875
+generator_first: true
+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: 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_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/feats_stats.npz
+tts: joint_text2wav
+tts_conf:
+    text2mel_type: fastspeech2
+    text2mel_params:
+        adim: 384
+        aheads: 2
+        conformer_activation_type: swish
+        conformer_dec_kernel_size: 31
+        conformer_enc_kernel_size: 7
+        conformer_pos_enc_layer_type: rel_pos
+        conformer_self_attn_layer_type: rel_selfattn
+        decoder_normalize_before: false
+        decoder_type: conformer
+        dlayers: 4
+        dunits: 1536
+        duration_predictor_chans: 256
+        duration_predictor_kernel_size: 3
+        duration_predictor_layers: 2
+        elayers: 4
+        encoder_normalize_before: false
+        encoder_type: conformer
+        energy_embed_dropout: 0.0
+        energy_embed_kernel_size: 1
+        energy_predictor_chans: 256
+        energy_predictor_dropout: 0.5
+        energy_predictor_kernel_size: 3
+        energy_predictor_layers: 2
+        eunits: 1536
+        init_type: xavier_uniform
+        pitch_embed_dropout: 0.0
+        pitch_embed_kernel_size: 1
+        pitch_predictor_chans: 256
+        pitch_predictor_dropout: 0.5
+        pitch_predictor_kernel_size: 5
+        pitch_predictor_layers: 5
+        positionwise_conv_kernel_size: 3
+        positionwise_layer_type: conv1d
+        postnet_chans: 256
+        postnet_filts: 5
+        postnet_layers: 5
+        reduction_factor: 1
+        stop_gradient_from_energy_predictor: false
+        stop_gradient_from_pitch_predictor: true
+        transformer_dec_attn_dropout_rate: 0.2
+        transformer_dec_dropout_rate: 0.2
+        transformer_dec_positional_dropout_rate: 0.2
+        transformer_enc_attn_dropout_rate: 0.2
+        transformer_enc_dropout_rate: 0.2
+        transformer_enc_positional_dropout_rate: 0.2
+        use_cnn_in_conformer: true
+        use_macaron_style_in_conformer: true
+        use_masking: true
+        idim: 78
+        odim: 80
+    vocoder_type: hifigan_generator
+    vocoder_params:
+        bias: true
+        channels: 512
+        in_channels: 80
+        kernel_size: 7
+        nonlinear_activation: LeakyReLU
+        nonlinear_activation_params:
+            negative_slope: 0.1
+        out_channels: 1
+        resblock_dilations:
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        -   - 1
+            - 3
+            - 5
+        resblock_kernel_sizes:
+        - 3
+        - 7
+        - 11
+        upsample_kernel_sizes:
+        - 16
+        - 16
+        - 4
+        - 4
+        upsample_scales:
+        - 8
+        - 8
+        - 2
+        - 2
+        use_additional_convs: true
+        use_weight_norm: true
+    discriminator_type: hifigan_multi_scale_multi_period_discriminator
+    discriminator_params:
+        follow_official_norm: true
+        period_discriminator_params:
+            bias: true
+            channels: 32
+            downsample_scales:
+            - 3
+            - 3
+            - 3
+            - 3
+            - 1
+            in_channels: 1
+            kernel_sizes:
+            - 5
+            - 3
+            max_downsample_channels: 1024
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            out_channels: 1
+            use_spectral_norm: false
+            use_weight_norm: true
+        periods:
+        - 2
+        - 3
+        - 5
+        - 7
+        - 11
+        scale_discriminator_params:
+            bias: true
+            channels: 128
+            downsample_scales:
+            - 4
+            - 4
+            - 4
+            - 4
+            - 1
+            in_channels: 1
+            kernel_sizes:
+            - 15
+            - 41
+            - 5
+            - 3
+            max_downsample_channels: 1024
+            max_groups: 16
+            nonlinear_activation: LeakyReLU
+            nonlinear_activation_params:
+                negative_slope: 0.1
+            out_channels: 1
+        scale_downsample_pooling: AvgPool1d
+        scale_downsample_pooling_params:
+            kernel_size: 4
+            padding: 2
+            stride: 2
+        scales: 3
+    generator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    discriminator_adv_loss_params:
+        average_by_discriminators: false
+        loss_type: mse
+    use_feat_match_loss: true
+    feat_match_loss_params:
+        average_by_discriminators: false
+        average_by_layers: false
+        include_final_outputs: true
+    use_mel_loss: 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_text2mel: 1.0
+    lambda_adv: 1.0
+    lambda_mel: 45.0
+    lambda_feat_match: 2.0
+    sampling_rate: 22050
+    segment_size: 32
+    cache_generator_outputs: true
+pitch_extract: dio
+pitch_extract_conf:
+    reduction_factor: 1
+    fs: 22050
+    n_fft: 1024
+    hop_length: 256
+    f0max: 400
+    f0min: 80
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+    stats_file: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/pitch_stats.npz
+energy_extract: energy
+energy_extract_conf:
+    reduction_factor: 1
+    fs: 22050
+    n_fft: 1024
+    hop_length: 256
+    win_length: null
+energy_normalize: global_mvn
+energy_normalize_conf:
+    stats_file: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/decode_use_teacher_forcingtrue_train.loss.best/stats/train/energy_stats.npz
+required:
+- output_dir
+- token_list
+version: 0.10.3a1
+distributed: true

exp/tts_finetune_joint_conformer_fastspeech2_hifigan.v8_raw_phn_tacotron_g2p_en_no_space/train.total_count.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18381c8d0f64ad79436883cf8d027eeb7974b7f98cec69475720855381b38bc
+size 620334354

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.3a2
+files:
+  model_file: exp/tts_finetune_joint_conformer_fastspeech2_hifigan.v8_raw_phn_tacotron_g2p_en_no_space/train.total_count.ave_5best.pth
+python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
+timestamp: 1631237823.97896
+torch: 1.7.1
+yaml_files:
+  train_config: exp/tts_finetune_joint_conformer_fastspeech2_hifigan.v8_raw_phn_tacotron_g2p_en_no_space/config.yaml