k2-fsa / sherpa-ncnn

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
https://k2-fsa.github.io/sherpa/ncnn/index.html
Apache License 2.0
1.08k stars 160 forks source link

长热词导致端点检测失效的NCNN流式语音识别模型问题 #318

Open 20246688 opened 9 months ago

20246688 commented 9 months ago

较长热词(比如四个字及以上)影响ncnn流式语音识别模型正常工作,比如python-api-examples/speech-recognition-from-microphone-with-endpoint-detection.py中添加hotwords_file=r"\sherpa-ncnn-streaming-zipformer-bilingual-zh-en-2023-02-13\hotwords_mix.txt",hotwords_score=2.0后,识别到热词时会在当前行序号立马结束识别,仿佛是端点检测失效一般。

pkufool commented 8 months ago

https://github.com/k2-fsa/sherpa-ncnn/pull/281#issuecomment-1972405448

20246688 commented 8 months ago

请问您提供的方法怎么使用?我使用的是里面的一个py代码。但是看不明白里面说的finalize方法是干嘛的,是直接写在 if is_endpoint:if result:里面吗,如果是需要重新编译库,可不可以开个教程视频啊?因为我用的python操作sherpa-ncnn模型的,也是偶然在哔站看见的,完全不明白所谓的finalize在哪里使用

------------------ 原始邮件 ------------------ 发件人: "Wei @.>; 发送时间: 2024年3月4日(星期一) 晚上7:18 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [k2-fsa/sherpa-ncnn] 长热词导致端点检测失效的NCNN流式语音识别模型问题 (Issue #318)

同 #281 (comment)

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>