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

Opened this issue · 2 comments

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。