如何在Python中使用语音识别自动检测语言

pip install SpeechRecognition pydub langdetect

import speech_recognition as sr
from langdetect import detect
from pydub import AudioSegment

# 将音频文件转换为WAV格式（如果需要）
def convert_to_wav(input_file, output_file):
    audio = AudioSegment.from_file(input_file)
    audio.export(output_file, format="wav")

# 语音识别函数
def recognize_speech_from_audio(file_path):
    recognizer = sr.Recognizer()
    with sr.AudioFile(file_path) as source:
        audio = recognizer.record(source)
    try:
        text = recognizer.recognize_google(audio)
        return text
    except sr.UnknownValueError:
        print("Google Speech Recognition could not understand audio")
    except sr.RequestError as e:
        print(f"Could not request results from Google Speech Recognition service; {e}")
    return None

# 语言检测函数
def detect_language(text):
    try:
        language = detect(text)
        return language
    except Exception as e:
        print(f"Error detecting language: {e}")
    return None

# 主函数
def main():
    input_audio_file = "path/to/your/audio/file"  # 输入音频文件路径
    wav_audio_file = "converted_audio.wav"  # 转换后的WAV文件路径

    # 将音频文件转换为WAV格式
    convert_to_wav(input_audio_file, wav_audio_file)

    # 进行语音识别
    recognized_text = recognize_speech_from_audio(wav_audio_file)
    if recognized_text:
        print(f"Recognized Text: {recognized_text}")

        # 进行语言检测
        language = detect_language(recognized_text)
        if language:
            print(f"Detected Language: {language}")

if __name__ == "__main__":
    main()