From 43c1424b0e2cf5621e8076fb78d22b758921b341 Mon Sep 17 00:00:00 2001 From: aceforeverd Date: Fri, 29 Aug 2025 10:48:15 +0800 Subject: [PATCH] docs: update readme --- Dockerfile | 5 +++-- README.md | 30 +++++++++++++++--------------- 2 files changed, 18 insertions(+), 17 deletions(-) diff --git a/Dockerfile b/Dockerfile index 7224fbd..21edfbd 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,12 +1,13 @@ FROM git.modelhub.org.cn:9443/enginex-metax/maca-c500-pytorch:2.33.0.6-torch2.6-py310-ubuntu24.04-amd64 RUN /opt/conda/bin/pip install funasr modelscope huggingface_hub +RUN /opt/conda/bin/pip install openai-whisper -RUN chmod 1777 -R /tmp && apt update && apt install -y ffmpeg +# RUN chmod 1777 -R /tmp && apt update && apt install -y ffmpeg WORKDIR /opt/app COPY ./ ./ RUN /opt/conda/bin/pip install -r requirements.txt EXPOSE 80 -ENTRYPOINT ["python3", "./test_funasr.py"] +ENTRYPOINT ["/opt/conda/bin/python3", "./test_funasr.py"] diff --git a/README.md b/README.md index 16ae212..044db23 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ # 沐曦 MetaX C500 FunASR ## 镜像构造 -```shell +```bash docker build -t . ``` @@ -9,19 +9,19 @@ docker build -t . ### 快速镜像测试 对funasr的测试需要在以上构造好的镜像容器内测试，测试步骤 1. 本项目中附带上了示例测试数据，音频文件为`lei-jun-test.wav`，音频的识别准确内容文件为`lei-jun.txt`，用户需要准备好相应的ASR模型路径，本例中假设我们已经下载好了SenseVoiceSmall模型存放于/model/SenseVoiceSmall -2. 在本项目路径下执行以下快速测试命令 -```shell -metax-docker run -it \ - --gpus=[0] \ - -v $PWD:/tmp/workspace \ - -v /model:/model \ - -e MODEL_DIR=/model/SenseVoiceSmall \ - -e TEST_FILE=lei-jun-test.wav \ - -e ANSWER_FILE=lei-jun.txt \ - -e RESULT_FILE=result.json \ - --cpus=4 --memory=16g \ - -``` +2. 在本项目路径下执行以下快速测试命令, 如果安装了 [metax-docker](https://developer.metax-tech.com/softnova/category?package_kind=Cloud&dimension=metax&chip_name=%E6%9B%A6%E4%BA%91C500%E7%B3%BB%E5%88%97&deliver_type=%E5%88%86%E5%B1%82%E5%8C%85&series_name=metax-docker): + ```bash + metax-docker run -it \ + --gpus=[0] \ + -v $PWD:/tmp/workspace \ + -v /model:/model \ + -e MODEL_DIR=/model/SenseVoiceSmall \ + -e TEST_FILE=lei-jun-test.wav \ + -e ANSWER_FILE=lei-jun.txt \ + -e RESULT_FILE=result.json \ + --cpus=4 --memory=16g \ + + ``` 上述测试指令成功运行将会在terminal中看到对测试音频的识别结果，运行时间以及1-cer效果指标，并且当前文件下会生成一个`result.json`文件记录刚才的测试结果 ### 定制化手动运行 @@ -37,4 +37,4 @@ metax-docker run -it \ | whisper | https://www.modelscope.cn/models/iic/Whisper-large-v3 | 23.8337 | ? | 0.910150 | ? | | | paraformer | https://modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch | 3.9888 | 4.8517 | 0.955075 | 0.955075 | | | conformer | https://www.modelscope.cn/models/iic/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch | 80.4228 | 78.2914 | 0.349418 | 0.346090 | | -| uni_asr | https://www.modelscope.cn/models/iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline | 90.8399 | 68.6999 | 0.717138 | 0.717138 | 该部分的适配修改了一些funASR源码 | +| uni_asr | https://www.modelscope.cn/models/iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline | 90.8399 | 68.6999 | 0.717138 | 0.717138 | |