search

k2-fsa / sherpa-onnx

Speech-to-text, text-to-speech, speaker recognition, 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
https://k2-fsa.github.io/sherpa/onnx/index.html
Apache License 2.0
3.11k stars 360 forks source link

说话人识别繁体字问题 #869

Closed 20246688 closed 4 months ago

20246688 commented 4 months ago

配置：win10 bat文件： @echo off CHCP 65001 set PYTHONIOENCODING=utf-8 python test.py ^ --silero-vad-model=./sherpa-onnx/silero_vad.onnx ^ --threshold=0.2 ^ --model=./sherpa-onnx/3dspeaker_speech_eres2net_large_sv_zh-cn_3dspeaker_16k.onnx ^ --speaker-file=./speaker.txt echo ok pause

speaker.txt Jack ./wav-library/ai-jack-1.wav Jack ./wav-library/ai-jack-2.wav Jack ./wav-library/ai-jack-3.wav lulu ./wav-library/ai-lulu-1.wav lulu ./wav-library/ai-lulu-2.wav lulu ./wav-library/ai-lulu-3.wav 中文 ./wav-library/ce-1.wav 中文 ./wav-library/ce-2.wav 中文 ./wav-library/ce-3.wav

请问输出的时候为什么是繁体字

20246688 commented 4 months ago

def load_speaker_file(args) -> Dict[str, List[str]]: if not Path(args.speaker_file).is_file(): raise ValueError(f"--speaker-file {args.speaker_file} does not exist")

ans = defaultdict(list)
with open(args.speaker_file, encoding='utf-8') as f:   已解决，谢谢！
csukuangfj commented 4 months ago

请截个图，哪里有繁体字？

20246688 commented 4 months ago

非常抱歉，我目前已修改了代码，复现不了之前的问题了，但问题可以通过修改sherpa-onnx\python-api-examples\speaker-identification-with-vad.py里面的def load_speaker_file(args) -> Dict[str, List[str]]:里的with open(args.speaker_file, encoding='utf-8') as f，应该是Win10操作系统或者bat文件的读编码习惯的问题，演示视频应该是在Linux使用的。

csukuangfj commented 4 months ago

ok, 那这个 issue, 可以关了么

20246688 commented 4 months ago

嗯嗯