Python基于Streamlit实现音频处理示例详解

# 安装依赖库
pip install streamlit streamlit-webrtc audio-recorder-streamlit openai-whisper python-dotx

import streamlit as st
from audio_recorder_streamlit import audio_recorder
import whisper
import os
from datetime import datetime

# 初始化模型
@st.cache_resource
def load_whisper_model():
    return whisper.load_model("base")  # 使用基础版模型

model = load_whisper_model()

# 界面布局
st.title("🎤 音频处理工作流")
col1, col2 = st.columns(2)

with col1:
    # 音频录制组件
    audio_bytes = audio_recorder(
        text="点击录音",
        recording_color="#e87070",
        neutral_color="#6aa36f",
        icon_name="microphone",
        sample_rate=16000
    )
    
    # 保存录音文件
    if audio_bytes:
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
        audio_path = f"audio_{timestamp}.wav"
        with open(audio_path, "wb") as f:
            f.write(audio_bytes)
        st.session_state.audio_path = audio_path
        st.audio(audio_bytes, format="audio/wav")

with col2:
    # 语音转文本功能
    if 'audio_path' in st.session_state and st.button("开始转换"):
        progress_bar = st.progress(0)
        status_text = st.empty()
        
        try:
            status_text.text("加载音频文件...")
            progress_bar.progress(20)
            
            # 使用Whisper进行转换
            status_text.text("语音识别中...")
            result = model.transcribe(st.session_state.audio_path)
            progress_bar.progress(80)
            
            # 显示结果
            st.subheader("转换结果")
            st.code(result["text"], language="text")
            st.session_state.text_result = result["text"]
            
            # 生成下载按钮
            with st.expander("下载选项"):
                st.download_button(
                    label="下载文本",
                    data=st.session_state.text_result,
                    file_name=f"transcript_{timestamp}.txt",
                    mime="text/plain"
                )
                
                with open(st.session_state.audio_path, "rb") as f:
                    st.download_button(
                        label="下载音频",
                        data=f,
                        file_name=audio_path,
                        mime="audio/wav"
                    )
            
            progress_bar.progress(100)
            status_text.text("处理完成！")
            
        except Exception as e:
            st.error(f"处理失败: {str(e)}")
            progress_bar.progress(0)

# 在HuggingFace Spaces部署时添加配置
STREAMLIT_SERVER_PORT = 8501

model = whisper.load_model("base", device="cuda")

import matplotlib.pyplot as plt
from scipy.io import wavfile

rate, data = wavfile.read(audio_path)
plt.specgram(data, Fs=rate)
st.pyplot(plt)

# requirements.txt
streamlit>=1.28
openai-whisper==20231106
audio-recorder-streamlit==0.1.7

# 监控内存使用
ps -o pid,user,%mem,command ax | grep streamlit