在fastapi中使用funasr把语音识别成文字

pip install fastapi uvicorn funasr torch torchaudio

import base64
import os
from fastapi import FastAPI, File, UploadFile, HTTPException
from funasr import AutoModel
from pydantic import BaseModel

# 初始化FastAPI应用
app = FastAPI()

# 加载FunASR模型
model = AutoModel(model="paraformer-zh")

# 定义请求体模型
class ASRResponse(BaseModel):
    text: str

# 定义接口
@app.post("/asr", response_model=ASRResponse)
async def asr(file: UploadFile = File(...)):
    try:
        # 保存上传的音频文件
       file_path = "temp.wav"
        with open(file_path, "wb") as f:
            f.write(await file.read())

        # 使用FunASR进行语音识别
       result = model.generate(input=file_path)

        # 删除临时文件
       os.remove(file_path)

        # 返回识别结果
       return {"text": result[0]['text']}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

# 启动服务
if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=8000)

python main.py