initial import from https://zenodo.org/record/3989498#.X90RlOlKjkM

README.md

@@ -0,0 +1,96 @@
+---
+tags:
+- espnet
+- audio
+- tts
+language: en
+datasets:
+- ljspeech
+license: cc-by-4.0
+inference: false
+---
+
+## ESPnet2 model `kan-bayashi/ljspeech_tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.best`
+
+♻️ Imported from https://zenodo.org/record/3989498#.X90RlOlKjkM
+
+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}
+}
+@inproceedings{inaguma-etal-2020-espnet,
+    title = "{ESP}net-{ST}: All-in-One Speech Translation Toolkit",
+    author = "Inaguma, Hirofumi  and
+      Kiyono, Shun  and
+      Duh, Kevin  and
+      Karita, Shigeki  and
+      Yalta, Nelson  and
+      Hayashi, Tomoki  and
+      Watanabe, Shinji",
+    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
+    month = jul,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://www.aclweb.org/anthology/2020.acl-demos.34",
+    pages = "302--311",
+}
+```
+
+
+### Training config
+
+See full config in [`config.yaml`](./config.yaml)
+
+```yaml
+config: conf/tuning/train_tacotron2.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_train_tacotron2_raw
+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
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+```
+
+

config.yaml

@@ -0,0 +1,232 @@
+config: conf/tuning/train_tacotron2.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_train_tacotron2_raw
+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
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 200
+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
+grad_clip: 1.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+log_interval: null
+pretrain_path: []
+pretrain_key: []
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 5120000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw/train/text_shape.phn
+- exp/tts_stats_raw/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw/valid/text_shape.phn
+- exp/tts_stats_raw/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
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 0.001
+    eps: 1.0e-06
+    weight_decay: 0.0
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- ..
+- OY0
+- UH0
+- AW0
+- '!'
+- OY2
+- '?'
+- UH2
+- ER2
+- ''''
+- AA0
+- IY2
+- AW2
+- AY0
+- AH2
+- UW2
+- AE0
+- OW2
+- ZH
+- AO2
+- EY0
+- OY1
+- EH0
+- UW0
+- AA2
+- AY2
+- AE2
+- IH2
+- AO0
+- EY2
+- OW0
+- EH2
+- UH1
+- TH
+- AW1
+- Y
+- JH
+- CH
+- ER1
+- G
+- NG
+- SH
+- OW1
+- .
+- AY1
+- EY1
+- AO1
+- IY0
+- UW1
+- IY1
+- HH
+- B
+- AA1
+- ','
+- F
+- ER0
+- V
+- AH1
+- AE1
+- P
+- W
+- EH1
+- M
+- IH0
+- IH1
+- Z
+- K
+- DH
+- L
+- R
+- S
+- D
+- T
+- N
+- AH0
+- <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:
+    fs: 22050
+    fmin: 80
+    fmax: 7600
+    n_mels: 80
+    hop_length: 256
+    n_fft: 1024
+    win_length: null
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/feats_stats.npz
+tts: tacotron2
+tts_conf:
+    embed_dim: 512
+    elayers: 1
+    eunits: 512
+    econv_layers: 3
+    econv_chans: 512
+    econv_filts: 5
+    atype: location
+    adim: 512
+    aconv_chans: 32
+    aconv_filts: 15
+    cumulate_att_w: true
+    dlayers: 2
+    dunits: 1024
+    prenet_layers: 2
+    prenet_units: 256
+    postnet_layers: 5
+    postnet_chans: 512
+    postnet_filts: 5
+    output_activation: null
+    use_batch_norm: true
+    use_concate: true
+    use_residual: false
+    dropout_rate: 0.5
+    zoneout_rate: 0.1
+    reduction_factor: 1
+    spk_embed_dim: null
+    use_masking: true
+    bce_pos_weight: 5.0
+    use_guided_attn_loss: true
+    guided_attn_loss_sigma: 0.4
+    guided_attn_loss_lambda: 1.0
+required:
+- output_dir
+- token_list
+distributed: false

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.8.0
+files:
+  model_file: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/199epoch.pth
+python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
+timestamp: 1597749894.186349
+torch: 1.6.0
+yaml_files:
+  train_config: exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/config.yaml

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fe4e34e9260b0970b20d6d5b27fa9355024713f4cc51ad14f87ee8d6518407
+size 106846941