FunASR
FunASR copied to clipboard
docker 使用sensevoice 模型不能加载LM模型
启动容器:
docker run -p 10096:10095 -it --privileged=true
-v $PWD/funasr-runtime-resources/models:/workspace/models
registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12
运行脚本:
nohup bash run_server_2pass.sh
--download-model-dir /workspace/models
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx
--model-dir iic/SenseVoiceSmall-onnx
--online-model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx
--punc-dir damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst
--itn-dir thuduj12/fst_itn_zh
--hotword /workspace/models/hotwords.txt > log.txt 2>&1 &
使用的是sensevoice模型,启动日志提示:LM model is not set, not executed,实际已指定了LM模型的路径
同样的脚本参数,如果--model-dir换成damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx或者damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx是可以正常加载LM模型的