# 引用whisper模块
import whisper
from flask import Flask,request
import datetime
import requests
import torch
import os

# 语音识别模型
# model = whisper.load_model("large", download_root="/opt/Whisper/models")    # 同时下载模型
#device = torch.device("cpu")    
device = torch.device("cuda:0")                                                  # 使用CPU加载模型
model = whisper.load_model("/opt/Whisper/models/tiny.pt", device=device)  # 加载模型
#model = whisper.load_model("D:\\whisper\\models\\tiny\\tiny.pt", device=device)  # 加载本地模型

# 实例化一个web服务对象
app = Flask(__name__)
# 构造一个接受post请求的响应
@app.route('/',methods=['POST'])
def postRequest():
    data = {}
    data['data'] = {'text':'Not Found!'}
    data['code'] = 404

    # # 验证秘钥是否通过
    # key = request.form.get('key')
    # if key != "OpenAI Whisper":
    #     data['data'] = {'text':'No permissions!'}
    #     data['code'] = 400
    #     return data

    # 判断翻译类型
    lang = 'zh'
    lang_ = request.form.get('lang')
    if lang_ == 'en':
        lang = 'en'

    # 验证是否上传文件，未上传文件使用远程地址或本地地址
    if 'file' not in request.files:

        # 获取路径
        path = request.form.get('path')
        if path.lower().endswith((".wav", ".WAV",".mp3",".MP3")) is False:
            data['data'] = {'text':'No wav or mp3!'}
            data['code'] = 400
            return data
        typ = request.form.get('typ') # url/path

        # 如果是使用连接，则远程拷贝链接文件到指定地址
        if typ == 'url':
            # 指定地址
            fileName = '/opt/Whisper/voice/' + datetime.datetime.now().strftime('%Y%m%d_%H%M%S') + '.wav'
            #fileName = 'D:\\whisper\\voice\\' + datetime.datetime.now().strftime('%Y%m%d_%H%M%S') + '.wav'
            
            downlaod(path, fileName)
            res = toLang(lang, fileName) # model.transcribe(fileName,language='Chinese')
            data['data'] = res
            data['code'] = 200
        # 如果是使用本地文件，则直接读取
        elif typ == 'path':
            res = toLang(lang, path) # model.transcribe(path,language='Chinese')
            data['data'] = res
            data['code'] = 200

    # 如果通过上传文件
    else:
        file = request.files['file']
        if file.filename == '':
            data['data'] = {'text':'No file!'}
            data['code'] = 400
            return data

        # 指定文件保存路径
        file_extension = file.filename.split(".")[-1]

        if file_extension != 'wav' and file_extension!= 'WAV' and file_extension != 'mp3' and file_extension!= 'MP3':
            data['data'] = {'text':'No Voice!'}
            data['code'] = 400
            return data

        # 指定地址
        fileName = '/opt/Whisper/voice/' + datetime.datetime.now().strftime('%Y%m%d_%H%M%S') + '.' + file_extension
        #fileName = 'D:\\whisper\\voice\\' + datetime.datetime.now().strftime('%Y%m%d_%H%M%S') + '.' + file_extension
        file.save(fileName)
        # 确保文件被写入磁盘
        with open(fileName, 'a') as f:
            f.flush()
            os.fsync(f.fileno())
        #语音钻文字    
        res = toLang(lang, fileName) # model.transcribe(fileName,language='Chinese')
        data['data'] = res
        data['code'] = 200
        
    return data

# 文件下载
def downlaod(url, file_path):
  headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:68.0) Gecko/20100101 Firefox/68.0"
  }
  r = requests.get(url=url, headers=headers)
  with open(file_path, "wb") as f:
    f.write(r.content)
    f.flush()

# 识别
def toLang(lang, file_path):
    print(file_path)
    if lang == 'en':
        prompt = 'is English'
        transcription = model.transcribe(file_path, language='en',verbose=True, initial_prompt=prompt)
        print(transcription["text"])
    else:
        prompt = '以下是普通话的句子'
        transcription = model.transcribe(file_path, language='zh',verbose=True, initial_prompt=prompt)
        print(transcription["text"])
    # 删除临时文件
    try:
        os.remove(file_path)
        print(f"Deleted file: {file_path}")
    except Exception as e:
        print(f"Failed to delete file: {file_path}, Error: {str(e)}")

    return transcription

if __name__ == '__main__':
    # 运行服务，并确定服务运行的IP和端口
    app.run('0.0.0.0', '8000')

nohup /home/wwwccczzz/anaconda3/envs/whisper/bin/python /opt/Whisper/speech.py > /opt/Whisper/speech.log 2>&1 &

  crontab -e

@reboot nohup /home/wwwccczzz/anaconda3/envs/whisper/bin/python /opt/Whisper/speech.py > /opt/Whisper/speech.log 2>&1 &