使用PYthon进行编程实现语音识别功能

# coding=utf-8 # WELCOME TO MING BRO's WORLD # THE MEETING TIME 2024/12/17 16:26 import pyttsx3 import whisper import speech_recognition as sr import time import numpy as np import pyaudio import wave from tqdm import tqdm def speak(audioString): print(audioString) pyttsx3.speak(audioString) engine = pyttsx3.init() engine.say("你是谁") engine.runAndWait() speak("I will speak this text") # 加载 Whisper 模型 model = whisper.load_model("base") #离线识别语音 # result = model.transcribe("zh.wav") # print(result['text']) def record_audio(wave_out_path,record_second): CHUNK = 1024 FORMAT = pyaudio.paInt16 CHANNELS = 1 RATE = 44100 p = pyaudio.PyAudio() stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK) wf = wave.open(wave_out_path, 'wb') wf.setnchannels(CHANNELS) wf.setsampwidth(p.get_sample_size(FORMAT)) wf.setframerate(RATE) print("* recording") for i in tqdm(range(0, int(RATE / CHUNK * record_second))): data = stream.read(CHUNK) wf.writeframes(data) print("* done recording") stream.stop_stream() stream.close() p.terminate() wf.close() # record_audio("output.mp3",record_second=4) # text = model.transcribe("M500000yLI8y2RJRq3.mp3") # print(text) def process_audio_data(audio_chunk): """ 将音频块数据转换为模型可以处理的格式。 """ audio_data = np.frombuffer(audio_chunk, dtype=np.int16).astype(np.float32) / 32768.0 return audio_data def transcribe_audio(audio_data): """ 使用 Whisper 模型对音频数据进行转录。 """ result = model.transcribe(audio_data, fp16=False) return result['text'] def main(): # 配置 PyAudio p = pyaudio.PyAudio() stream = p.open(format=pyaudio.paInt16, channels=1, rate=44100, input=True, frames_per_buffer=1024) print("开始实时语音识别...") time.sleep(10) try: while True: # 读取音频块 audio_chunk = stream.read(1024) # 处理音频数据 audio_data = process_audio_data(audio_chunk) # 转录音频数据 # text = transcribe_audio("output.mp3") text = transcribe_audio(audio_data) # 输出转录结果 print(text) except KeyboardInterrupt: print("\n停止实时语音识别.") finally: # 关闭音频流 stream.stop_stream() stream.close() p.terminate() if __name__ == "__main__": main() # # # 录下来你讲的话 # def recordAudio(): # # 用麦克风记录下你的话 # print("开始麦克风记录下你的话") # r = sr.Recognizer() # with sr.Microphone() as source: # audio = r.listen(source) # data = "" # try: # data = r.recognize_google(audio) # print("You said: " + data) # except sr.UnknownValueError: # print("Google Speech Recognition could not understand audio") # except sr.RequestError as e: # print("Could not request results from Google Speech Recognition service; {0}".format(e)) # return data # # # if __name__ == '__main__': # time.sleep(2) # while True: # data = recordAudio() # print(data)