Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
fangd123 9ef6c9c01d | 8 months ago | |
---|---|---|
.dockerignore | 8 months ago | |
Dockerfile | 8 months ago | |
README.md | 8 months ago | |
README_EN.md | 8 months ago | |
app.py | 8 months ago | |
main.py | 8 months ago | |
modelscope_speaker_seperate2.py | 8 months ago | |
onnx_demo.py | 8 months ago | |
paraformer.py | 8 months ago | |
requirements.txt | 8 months ago | |
speaker_seperate.py | 8 months ago | |
speaker_seperate1.py | 8 months ago | |
tts.py | 8 months ago | |
utils.py | 1 year ago |
这是一个基于 FastAPI 的语音转录服务。用户可以上传音频文件,服务会将其转换为文本。
modelscope.pipelines
进行语音识别。/transcribe/
端点以上传音频文件并获取转录文本。注:首次启动程序会从modelsope仓库拉取模型文件存储至本地,需要几分钟的时间。
pip install -r requirements.txt
。app.py
:python app.py
。0.0.0.0
上的端口 8100
上启动。使用你的浏览器或 API 工具访问。docker pull registry.cn-guangzhou.aliyuncs.com/fangd123/asr:1.0
# 若无GPU
docker run --name asr -p 8100:8100 registry.cn-guangzhou.aliyuncs.com/fangd123/asr:1.0
# 若有GPU(需要先安装NVIDIA Container Toolkit)
docker run --name asr --runtime=nvidia --gpus all -p 8100:8100 registry.cn-guangzhou.aliyuncs.com/fangd123/asr:1.0
docker build -t asr-service .
docker run -p 8100:8100 asr-service
0.0.0.0
上的端口 8100
上启动。/transcribe/
端点并上传您的音频文件。注:可访问/docs
端点进入调试界面
服务返回一个包含以下字段的 JSON 数组:
text
:转录的文本。start
:文本的开始时间(单位:毫秒)。end
:文本的结束时间(单位:毫秒)。text_seg
:分词文本。ts_list
:每段文本的时间戳列表。例如:
[
{
"text": " just time 哎,",
"start": 4090,
"end": 6470,
"text_seg": "just time 哎 ",
"ts_list": [
[4090, 4330],
[4470, 4875],
[6250, 6470]
]
},
...
]
试图将目前最好的语音识别模型整合在一起
Python Markdown Dockerfile Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》