STT python

1. 安装所需库

我们需要安装这两个库，在命令行中运行以下命令：

pip install SpeechRecognition pyaudio

2. 使用 SpeechRecognition 库

SpeechRecognition 是一个 Python 库，用于将语音转换为文本，以下是一个简单的示例，演示如何使用 SpeechRecognition 从麦克风捕获音频并将其转换为文本：

import speech_recognition as sr

def listenA():
    # 创建recognizer对象
    r = sr.Recognizer()

    # 打开麦克风
    with sr.Microphone() as source:
        print("请开始说话...")
        audio = r.listen(source)

    # 将语音转换为文本
    try:
        print("你说的是: " + r.recognize_google(audio, language='zh-CN'))
    except sr.UnknownValueError:
        print("无法理解语音")
    except sr.RequestError as e:
        print("语音服务无法访问或内部错误: {0}".format(e))

def speechRecognitionByMicrophone(languageType):
    # 创建语音识别对象
    recognizer = sr.Recognizer()
    # 打开麦克风获取语音
    with sr.Microphone() as source:
        print("Say something!")
        # 降噪
        recognizer.adjust_for_ambient_noise(source)
        # 收音
        audio = recognizer.listen(source)
    # 利用CMU Sphinx引擎进行语音识别
    try:
        text = recognizer.recognize_sphinx(audio, language=languageType)
        print(text)
        pyttsx3.speak(text)
    except sr.UnknownValueError:
        print("Sphinx could not understand audio")
    except sr.RequestError as e:
        print("Sphinx error: {0}".format(e))

遍历excel表 第一列并TTS

    from openpyxl import load_workbook

    # 加载Excel文件
    workbook = load_workbook('example.xlsx')

    # 遍历所有工作表
    for sheet_name in workbook.sheetnames:
        print(f"Worksheet: {sheet_name}")
        sheet = workbook[sheet_name]

        # 遍历工作表中的所有行
        for row in sheet.iter_rows(values_only=True):
            tts(str(row))

openAI whisper

whisper 依赖pytorch

pythorch 依赖torch-1.6.0-cp37-cp37m-win_amd64.whl

https://mirror.sjtu.edu.cn/pytorch-wheels/cu102/?mirror_intel_list
https://download.pytorch.org/whl/torch_stable.html

def listenwisper():
    # 创建recognizer对象
    r = sr.Recognizer()

    # 打开麦克风
    with sr.Microphone() as source:
        print("请开始说话...")
        audio = r.listen(source)

    model = whisper.load_model("tiny")
    result = model.transcribe(audio, fp16=False, language="Chinese")
    print(result["text"])
    return result["text"]