search

PaddlePaddle / PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
https://paddlespeech.readthedocs.io
Apache License 2.0
11.19k stars 1.86k forks source link

混合模型报错Please check config, am support: fastspeech2, voc support: hifigan_csmsc-zh or mb_melgan_csmsc. #3755

Open jianghuakun opened 6 months ago

jianghuakun commented 6 months ago

我下载模型fastspeech2_mix_onnx_0.2.0.zip， 然后将tts_online_ws_application.yaml中模型名称改为fastspeech2_mix，voc改为hifigan_csmsc。报错如下： [2024-04-29 08:39:32,162] [ ERROR] - Failed to start server. [2024-04-29 08:39:32,162] [ ERROR] - Please check config, am support: fastspeech2, voc support: hifigan_csmsc-zh or mb_melgan_csmsc.

使用命令行正常：paddlespeech tts --am fastspeech2_mix --voc hifigan_csmsc --lang mix --input "我们的声学模型使用了 Fast Speech Two, 声码器使用了 Parallel Wave GAN and Hifi GAN." --spk_id 175 --output mix_spk175.wav

Ray961123 commented 6 months ago

开发者你好，感谢关注 PaddleSpeech 开源项目，抱歉给你带来了不好的开发体验，目前开源项目维护人力有限，你可以尝试通过修改 PaddleSpeech 源码的方式自己解决，或请求开源社区其他开发者的协助。飞桨开源社区交流频道：飞桨AI Studio星河社区-人工智能学习与实训社区