"test/git@developer.sourcefind.cn:gaoqiong/yaml-cpp.git" did not exist on "091ddfa52d62d42021a00790aa7d2521af60c7e5"
README.md 1.77 KB
Newer Older
dcuai's avatar
dcuai committed
1
# ASR
chenxj's avatar
chenxj committed
2
3
## 论文

chenxj's avatar
chenxj committed
4
## 模型结构
chenzk's avatar
chenzk committed
5
![image](https://developer.sourcefind.cn/codes/modelzoo/asr_onnx/-/raw/main/resources/silero_stt_model.jpg)
dcuai's avatar
dcuai committed
6
## 算法原理
chenzk's avatar
chenzk committed
7
![image](https://developer.sourcefind.cn/codes/modelzoo/asr_onnx/-/raw/main/resources/asr.png)
chenxj's avatar
chenxj committed
8
9
10
## 数据集

## 环境配置
chenxj's avatar
chenxj committed
11
12
[光源](https://www.sourcefind.cn/#/service-details)可拉取推理的docker镜像,在[光合开发者社区](https://cancon.hpccube.com:65024/4/main/)可下载onnxruntime安装包。asr_onnx推荐的镜像如下:
```
shantf's avatar
shantf committed
13
14
15
16
17
18
19
20
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
cd asr_onnxruntime #进入当前项目目录
docker run -d -t --privileged --device=/dev/kfd --device=/dev/dri/ --network=host --group-add video -v /opt/hyhal:/opt/hyhal:ro -v `pwd`:/mnt --name=asr-test image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
docker exec -it asr-test /bin/bash
cd /mnt
pip install onnx -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pysoundfile -i https://pypi.tuna.tsinghua.edu.cn/simple

chenxj's avatar
chenxj committed
21
```
chenzk's avatar
chenzk committed
22
23
下载模型 (https://models.silero.ai/models/en/en_v5.onnx) 到当前目录,建立wavs文件夹添加测试wav文件。

chenxj's avatar
chenxj committed
24
## 推理
chenxj's avatar
chenxj committed
25
26
```
python3 main.py --model_dir="./en_v5.onnx" --wav_dir="./wavs/" --warmup=1
shantf's avatar
shantf committed
27
# --wav_dir:需要推理的语音路劲,如"./speech_orig.wav";speech_orig.wav是文件夹中已经存在的语音
chenxj's avatar
chenxj committed
28
```
dcuai's avatar
dcuai committed
29
## result
chenzk's avatar
chenzk committed
30
![image](https://developer.sourcefind.cn/codes/modelzoo/asr_onnx/-/raw/main/resources/asr_result.png)
chenxj's avatar
chenxj committed
31
32
33
34
35
36
37
### 精度
暂无
## 应用场景
### 算法类别
语音识别
### 热点应用行业
交通,金融,医疗,教育,家居
chenxj's avatar
chenxj committed
38
## 源码仓库及问题反馈
chenzk's avatar
chenzk committed
39
https://developer.sourcefind.cn/codes/modelzoo/asr_onnx
dcuai's avatar
dcuai committed
40
## 参考资料
chenxj's avatar
chenxj committed
41
* [silero-models](https://github.com/snakers4/silero-models)
sugon_cxj's avatar
sugon_cxj committed
42