Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift, Dart, JavaScript, Flutter, Object Pascal, Lazarus, Rust
3.66k
stars
425
forks
source link
vits-melo-tts-zh_en 模型疑问 #1552
Open
endink opened 3 days ago
endink
commented
3 days ago
当中文中遇到长段的英文时会明显出现性能下降，这可能是什么问题？这个模型有优化方案吗？这似乎是目前唯一的中英文混合模型，但是英文发音并不好，很多单词不会发音，看起来和 cum 字典有关