Views
No views yet
kan-bayashi/csmsc_tts_train_tacotron2_raw_phn_pypinyin_g2p_phone_train.loss.best1pip install torch
2pip install espnet_model_zoo1import soundfile
2from espnet2.bin.tts_inference import Text2Speech
3text2speech = Text2Speech.from_pretrained("espnet/kan-bayashi_csmsc_tts_train_tacotron2_raw_phn_pypinyin_g2p_phone_train.loss.best")
4
5text = "春江潮水连海平，海上明月共潮生"
6speech = text2speech(text)["wav"]
7soundfile.write("out.wav", speech.numpy(), text2speech.fs, "PCM_16")1@inproceedings{watanabe2018espnet,
2 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},
3 title={{ESPnet}: End-to-End Speech Processing Toolkit},
4 year={2018},
5 booktitle={Proceedings of Interspeech},
6 pages={2207--2211},
7 doi={10.21437/Interspeech.2018-1456},
8 url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
9}
10@inproceedings{hayashi2020espnet,
11 title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
12 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},
13 booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
14 pages={7654--7658},
15 year={2020},
16 organization={IEEE}
17}1@misc{watanabe2018espnet,
2 title={ESPnet: End-to-End Speech Processing Toolkit},
3 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},
4 year={2018},
5 eprint={1804.00015},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL}
8}