WhisperX 是一個優(yōu)秀的開源Python語音識別庫。
下面記錄Windows10系統(tǒng)下部署Whisper
1、在操作系統(tǒng)中安裝 Python環(huán)境
2、安裝 CUDA環(huán)境
3、安裝Annaconda或Minconda環(huán)境
4、下載安裝ffmpeg
下載release-builds包，如下圖所示

將下載的包解壓到你想要的路徑，然后配置系統(tǒng)環(huán)境：我的電腦->高級系統(tǒng)設(shè)置->環(huán)境變量->Path


設(shè)置完成后打開cmd窗口輸入

ffmpeg

5、conda環(huán)境安裝指定位置的虛擬環(huán)境

conda create --prefix=D:\Projects\LiimouDemo\WhisperX\Code\whisperX\whisperXVenv python=3.10

6、激活虛擬環(huán)境

conda activate D:\Projects\LiimouDemo\WhisperX\Code\whisperX\whisperXVenv

7、安裝WhisperX庫

pip install git+https://github.com/m-bain/whisperx.git

8、更新WhisperX庫

pip install git+https://github.com/m-bain/whisperx.git --upgrade

9、在Python中使用

import whisperx
import time
import zhconv
device = "cuda"
audio_file = "data/test.mp3"
batch_size = 16 # reduce if low on GPU mem
compute_type = "float16" # change to "int8" if low on GPU mem (may reduce accuracy)
# compute_type = "int8" # change to "int8" if low on GPU mem (may reduce accuracy)
print('開始加載模型')
start = time.time()
# 1. Transcribe with original whisper (batched)
model = whisperx.load_model("large-v2", device, compute_type=compute_type)
# model = whisperx.load_model("small", device, compute_type=compute_type)
end = time.time()
print('加載使用的時間：',end-start,'s')
start = time.time()
audio = whisperx.load_audio(audio_file)
result = model.transcribe(audio, batch_size=batch_size)

print(result["segments"][0]["text"]) # before alignment
end = time.time()
print('識別使用的時間：',end-start,'s')

封裝上述代碼，初始化時調(diào)用一次loadModel()方法，之后使用就直接調(diào)用asr(path)方法

import whisperx
import zhconv
from whisperx.asr import FasterWhisperPipeline
import time

class WhisperXTool:
    device = "cuda"
    audio_file = "data/test.mp3"
    batch_size = 16  # reduce if low on GPU mem
    compute_type = "float16"  # change to "int8" if low on GPU mem (may reduce accuracy)
    # compute_type = "int8" # change to "int8" if low on GPU mem (may reduce accuracy)
    fast_model: FasterWhisperPipeline

    def loadModel(self):
        # 1. Transcribe with original whisper (batched)
        self.fast_model = whisperx.load_model("large-v2", self.device, compute_type=self.compute_type)
        print("模型加載完成")

    def asr(self, filePath: str):
        start = time.time()
        audio = whisperx.load_audio(filePath)
        result = self.fast_model.transcribe(audio, batch_size=self.batch_size)
        s = result["segments"][0]["text"]
        s1 = zhconv.convert(s, 'zh-cn')
        print(s1)
        end = time.time()
        print('識別使用的時間：', end - start, 's')
        return s1

zhconv是中文簡體繁體轉(zhuǎn)換的庫，安裝命令如下文章來源地址http://www.zghlxwxcb.cn/news/detail-568326.html

pip install zhconv

到了這里，關(guān)于whisperX 語音識別本地部署的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！