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
10.74k stars 1.82k forks source link

TTS多音字问题 #3297

Open NLPerxue opened 1 year ago

NLPerxue commented 1 year ago

如题，“银行”、“行人”等模型可以正确识别；但是“欢迎来到我行办理业务”这种情况模型无法正确处理多音字，应该怎么解决？

zh794390558 commented 1 year ago

https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/paddlespeech/t2s/frontend/polyphonic.yaml 这里添加多音字。

NLPerxue commented 1 year ago

https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/paddlespeech/t2s/frontend/polyphonic.yaml 这里添加多音字。

感谢! 请问这个可以直接用在推理部署阶段吗？

stale[bot] commented 10 months ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

csukuangfj commented 9 months ago

@NLPerxue

可以看下 https://github.com/k2-fsa/sherpa-onnx/pull/409

纯 c++ 实现，并且还提供各种语言的 api, 比如 python/c/kotlin/swift/c#/go 等等。

think4j commented 3 months ago

已解决，在https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/paddlespeech/t2s/frontend/polyphonic.yaml这里添加多音字后，需要重新安装PaddleSpeech # 请确保目前处于PaddleSpeech项目的根目录 pip install . -i https://pypi.tuna.tsinghua.edu.cn/simple