FunASR icon indicating copy to clipboard operation
FunASR copied to clipboard

funasr-runtime-sdk-gpu-0.1.1版本运行过程中出现异常

Open liurongjie174 opened this issue 1 year ago • 3 comments

Notice: In order to resolve issues more efficiently, please raise issue following the template. (注意:为了更加高效率解决您遇到的问题,请按照模板提问,补充细节)

🐛 Bug

To Reproduce

Steps to reproduce the behavior (always include the command you ran):

多个客户端同时对funasr-runtime-sdk-gpu-0.1.1发送离线语音文件识别时,fun_asr_server服务端很容易出现异常崩溃。具体如下截图所示: 1崩溃 ,观察GPU显存还是很正常的。24G的显存才使用了4G多

Code sample

Expected behavior

Environment

  • OS (e.g., Linux):
  • FunASR Version (e.g., 1.0.0):
  • ModelScope Version (e.g., 1.11.0):
  • PyTorch Version (e.g., 2.0.0):
  • How you installed funasr (pip, source):
  • Python version:
  • GPU (e.g., V100M32)
  • CUDA/cuDNN version (e.g., cuda11.7):
  • Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
  • Any other relevant information:

Additional context

liurongjie174 avatar Sep 03 '24 12:09 liurongjie174

你想跑GPU,但是你的镜像是CPU版本的呀

xiaoheiNLP avatar Sep 06 '24 02:09 xiaoheiNLP

我是通过docker run --gpus=all -p 10095:10095 -it --privileged=true
-v $PWD/funasr-runtime-resources/models:/workspace/models
registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1 和 bash run_server.sh
--download-model-dir /workspace/models
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx
--model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-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 & 启动的服务,这是cpu版本的?

liurongjie174 avatar Sep 06 '24 03:09 liurongjie174

确定是GPU版本镜像,多个客户端(2个以上)同时请求的时候(遍历读取100多个录音),可能运行一阵子完,fun_asr_server服务端没有任何响应了,看gpu的显存已经变成1MB,实际上服务已经down掉了。该问题很容易复现

liurongjie174 avatar Sep 06 '24 06:09 liurongjie174