python离线语音识别库whisper

bob666zxj

推荐一个python离线语音识别库whisper
这是由openai发布的离线语音识别库，在github上有超过 65K 的Star
github：https://github.com/openai/whisper

下面是模型列表：

尺寸	参数数量	纯英语模式	多语言模型	所需 VRAM	相对速度
tiny	39 M	tiny.en	tiny	~1 GB	~32x
base	74 M	base.en	base	~1 GB	~16x
small	244 M	small.en	small	~2 GB	~6x
medium	769 M	medium.en	medium	~5 GB	~2x
large	1550 M	N/A	large	~10 GB	1x

运行环境：

需要ffmpeg，关于ffmpeg的下载请看这篇帖子https://www.52pojie.cn/thread-1950306-1-1.html

python代码：

import whisper
import zhconv

# 加载 whisper 模型，这里使用的是"tiny"版本
model = whisper.load_model("tiny")
'''
tiny    39 M    tiny.en     tiny     ~1 GB    ~32x
base    74 M    base.en     base     ~1 GB    ~16x
small   244 M   small.en    small    ~2 GB    ~6x
medium  769 M   medium.en   medium   ~5 GB    ~2x
large   1550 M  N/A     large    ~10 GB   1x
'''
# 使用加载的模型对"1.wav"文件进行语音转文字处理
result = model.transcribe("1.wav")
print(result)
# 将转录结果中的文本转换为简体中文
result=zhconv.convert(result["text"], 'zh-cn')
print(result)

如果没有下载模型会自动下载模型，无需科学。

1e3e

pip  install whisper -i https://mirrors.aliyun.com/pypi/simple
DEPRECATION: Loading egg at /home/q9/miniforge3/lib/python3.12/site-packages/muggle_ocr-1.0.3-py3.12.egg is deprecated. pip 24.3 will enforce this behaviour change. A possible replacement is to use pip for package installation.. Discussion can be found at https://github.com/pypa/pip/issues/12330
Looking in indexes: https://mirrors.aliyun.com/pypi/simple
Collecting whisper
  Downloading https://mirrors.aliyun.com/pypi/ ... isper-1.1.10.tar.gz (42 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.8/42.8 kB 171.9 kB/s eta 0:00:00
  Preparing metadata (setup.py) ... done
Requirement already satisfied: six in /home/q9/miniforge3/lib/python3.12/site-packages (from whisper) (1.16.0)
Building wheels for collected packages: whisper
  Building wheel for whisper (setup.py) ... done
  Created wheel for whisper: filename=whisper-1.1.10-py3-none-any.whl size=41120 sha256=b3be1aa7fe52541a79c44c072264887502d90bbe79ed11d253a027e18cbbfe94
  Stored in directory: /home/q9/.cache/pip/wheels/a4/25/9e/80873926d30e583ee8e318c6beda99127842c9f6a8302bd25f
Successfully built whisper
Installing collected packages: whisper
Successfully installed whisper-1.1.10
(base) q9@q9-pc:~/Sounds$ pip  install zhconv -i https://mirrors.aliyun.com/pypi/simple
DEPRECATION: Loading egg at /home/q9/miniforge3/lib/python3.12/site-packages/muggle_ocr-1.0.3-py3.12.egg is deprecated. pip 24.3 will enforce this behaviour change. A possible replacement is to use pip for package installation.. Discussion can be found at https://github.com/pypa/pip/issues/12330
Looking in indexes: https://mirrors.aliyun.com/pypi/simple
Collecting zhconv
  Downloading https://mirrors.aliyun.com/pypi/ ... zhconv-1.4.3.tar.gz (211 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 211.6/211.6 kB 162.7 kB/s eta 0:00:00
  Preparing metadata (setup.py) ... done
Building wheels for collected packages: zhconv
  Building wheel for zhconv (setup.py) ... done
  Created wheel for zhconv: filename=zhconv-1.4.3-py2.py3-none-any.whl size=208851 sha256=7328296dda4c1abed280c7ec3d706e54b15e232f183c0d9995ee2ab53212021e
  Stored in directory: /home/q9/.cache/pip/wheels/36/d7/70/203f9ffe67d4d69c7b46c31984013ced8046ef4c298294fca0
Successfully built zhconv
Installing collected packages: zhconv
Successfully installed zhconv-1.4.3
(base) q9@q9-pc:~/Sounds$ python sound.py
Traceback (most recent call last):
  File "/home/q9/Sounds/sound.py", line 5, in <module>
    model = whisper.load_model("tiny")
            ^^^^^^^^^^^^^^^^^^
AttributeError: module 'whisper' has no attribute 'load_model'

woaipochu

请问是只需要pip  install whisper -i https://mirrors.aliyun.com/pypi/simple

安装这个后，运行你上面的代码，他就会自动下载模型，然后显示运行结果了？
github这个里面的不用下载？

ImYoubaba

封装成DLL其他语言可以实时调用就给力了

anning666

代码看上去好简洁,简单粗暴解决问题...

Liebesfreud

代码看上去有种简洁美，不过我刚入门学，部署什么的还很生疏

sinmu

蹲一个实测效果

1e3e

大大，帮忙看看哈，不能运行的，安装库都是正常的。另外模型可以离线下载吗？

tzq001

太难了，才入门呢，就挑战这个了

bob666zxj

1e3e 发表于 2024-8-1 17:00
pip  install whisper -i https://mirrors.aliyun.com/pypi/simple
DEPRECATION: Loading egg at /home/q ...

这个问题我也不太清楚，我这里重装了whisper，也没能复现。你可以试一下卸载重新安装whisper。

WA83004197

蹲一个实测效果