* Add feature.

.gitignore

@@ -0,0 +1,68 @@
+# 虚拟环境
+venv/
+env/
+.env/
+*.venv/
+
+# 依赖文件
+__pycache__/
+*.py[cod]
+*$py.class
+
+# PyTorch相关
+*.pt
+*.pth
+
+# 编辑器配置
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# 日志文件
+logs/
+*.log
+
+# 测试输出
+.pytest_cache/
+.coverage
+coverage.xml
+
+# Docker相关
+.dockerignore
+docker-compose.override.yml
+
+# 环境变量
+.env
+.env.local
+.env.*.local
+
+# 构建输出
+build/
+dist/
+*.egg-info/
+
+# 操作系统文件
+.DS_Store
+Thumbs.db
+
+# 临时文件
+*.tmp
+*.temp
+.tmp/
+.temp/
+
+# Jupyter Notebook
+.ipynb_checkpoints/
+*.ipynb
+
+# 数据文件
+*.data
+*.csv
+*.jsonl
+
+# 模型文件
+models/
+.cache/
+.huggingface/

Dockerfile

@@ -3,6 +3,12 @@
 
 FROM python:3.9
 
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    ffmpeg \
+    libsndfile1 \
+    && rm -rf /var/lib/apt/lists/*
+
 RUN useradd -m -u 1000 user
 USER user
 ENV PATH="/home/user/.local/bin:$PATH"

app.py

@@ -1,8 +1,95 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import JSONResponse
+from fastapi.staticfiles import StaticFiles
+from faster_whisper import WhisperModel
+from transformers import pipeline
+import os
+import tempfile
+from pydub import AudioSegment
 
-app = FastAPI()
+app = FastAPI(title="智能音频转录与摘要服务")
+
+# 挂载静态文件目录，前端通过/front访问
+app.mount("/front", StaticFiles(directory="static", html=True), name="static")
+
+# 加载模型
+whisper_model = WhisperModel("medium", device="cpu", compute_type="int8")
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=-1)
 
 @app.get("/")
-def greet_json():
-    return {"Hello": "World!"}
+def root():
+    return {"message": "智能音频转录与摘要服务已启动"}
+
+@app.post("/transcribe")
+async def transcribe_audio(file: UploadFile = File(...)):
+    """上传音频文件，返回转录文本"""
+    try:
+        # 保存临时文件
+        with tempfile.NamedTemporaryFile(suffix=".tmp", delete=False) as temp_file:
+            temp_file.write(await file.read())
+            temp_file_path = temp_file.name
+        
+        # 转换为wav格式（如果不是）
+        audio = AudioSegment.from_file(temp_file_path)
+        wav_path = temp_file_path + ".wav"
+        audio.export(wav_path, format="wav")
+        
+        # 使用faster-whisper转录
+        segments, info = whisper_model.transcribe(wav_path, beam_size=5, language="zh")
+        transcription = "".join([segment.text for segment in segments])
+        
+        # 清理临时文件
+        os.unlink(temp_file_path)
+        os.unlink(wav_path)
+        
+        return JSONResponse(content={"transcription": transcription})
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+@app.post("/summarize")
+async def summarize_text(text: dict):
+    """对文本进行摘要"""
+    try:
+        transcription = text.get("text", "")
+        if not transcription:
+            return JSONResponse(content={"error": "没有提供文本"}, status_code=400)
+        
+        # 使用bart-large-cnn进行摘要
+        summary = summarizer(transcription, max_length=150, min_length=30, do_sample=False)
+        
+        return JSONResponse(content={"summary": summary[0]["summary_text"]})
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+@app.post("/process")
+async def process_audio(file: UploadFile = File(...)):
+    """上传音频文件，返回转录文本和摘要"""
+    try:
+        # 保存临时文件
+        with tempfile.NamedTemporaryFile(suffix=".tmp", delete=False) as temp_file:
+            temp_file.write(await file.read())
+            temp_file_path = temp_file.name
+        
+        # 转换为wav格式
+        audio = AudioSegment.from_file(temp_file_path)
+        wav_path = temp_file_path + ".wav"
+        audio.export(wav_path, format="wav")
+        
+        # 转录
+        segments, info = whisper_model.transcribe(wav_path, beam_size=5, language="zh")
+        transcription = "".join([segment.text for segment in segments])
+        
+        # 摘要
+        summary = summarizer(transcription, max_length=150, min_length=30, do_sample=False)
+        
+        # 清理临时文件
+        os.unlink(temp_file_path)
+        os.unlink(wav_path)
+        
+        return JSONResponse(content={
+            "transcription": transcription,
+            "summary": summary[0]["summary_text"]
+        })
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
 

requirements.txt

@@ -1,2 +1,10 @@
 fastapi
 uvicorn[standard]
+faster-whisper
+transformers
+torch
+pydub
+python-multipart
+accelerate
+optimum
+

static/index.html

@@ -0,0 +1,505 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>智能音频转录与摘要服务</title>
+    <style>
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+        }
+        
+        body {
+            font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            min-height: 100vh;
+            padding: 20px;
+        }
+        
+        .container {
+            max-width: 800px;
+            margin: 0 auto;
+            background: white;
+            border-radius: 12px;
+            box-shadow: 0 10px 40px rgba(0, 0, 0, 0.1);
+            overflow: hidden;
+        }
+        
+        .header {
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+            padding: 30px;
+            text-align: center;
+        }
+        
+        .header h1 {
+            font-size: 28px;
+            margin-bottom: 10px;
+        }
+        
+        .header p {
+            font-size: 16px;
+            opacity: 0.9;
+        }
+        
+        .content {
+            padding: 30px;
+        }
+        
+        .upload-section {
+            margin-bottom: 30px;
+        }
+        
+        .upload-area {
+            border: 2px dashed #667eea;
+            border-radius: 8px;
+            padding: 40px;
+            text-align: center;
+            cursor: pointer;
+            transition: all 0.3s ease;
+            margin-bottom: 20px;
+        }
+        
+        .upload-area:hover {
+            border-color: #764ba2;
+            background-color: #f8f9ff;
+        }
+        
+        .upload-area.dragover {
+            border-color: #764ba2;
+            background-color: #f0f4ff;
+        }
+        
+        .upload-area input[type="file"] {
+            display: none;
+        }
+        
+        .upload-area label {
+            cursor: pointer;
+            color: #667eea;
+            font-weight: 600;
+            display: block;
+            margin-bottom: 10px;
+        }
+        
+        .upload-area .file-info {
+            font-size: 14px;
+            color: #666;
+        }
+        
+        .btn-group {
+            display: flex;
+            gap: 10px;
+            margin-bottom: 30px;
+            flex-wrap: wrap;
+        }
+        
+        .btn {
+            padding: 12px 24px;
+            border: none;
+            border-radius: 6px;
+            font-size: 16px;
+            font-weight: 600;
+            cursor: pointer;
+            transition: all 0.3s ease;
+            flex: 1;
+            min-width: 150px;
+        }
+        
+        .btn-primary {
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+        }
+        
+        .btn-primary:hover {
+            transform: translateY(-2px);
+            box-shadow: 0 5px 15px rgba(102, 126, 234, 0.4);
+        }
+        
+        .btn-secondary {
+            background-color: #f0f2f5;
+            color: #666;
+        }
+        
+        .btn-secondary:hover {
+            background-color: #e4e6eb;
+        }
+        
+        .btn:disabled {
+            opacity: 0.6;
+            cursor: not-allowed;
+            transform: none;
+        }
+        
+        .progress-section {
+            margin-bottom: 30px;
+            display: none;
+        }
+        
+        .progress-bar {
+            width: 100%;
+            height: 8px;
+            background-color: #e0e0e0;
+            border-radius: 4px;
+            overflow: hidden;
+            margin-bottom: 10px;
+        }
+        
+        .progress-fill {
+            height: 100%;
+            background: linear-gradient(90deg, #667eea 0%, #764ba2 100%);
+            border-radius: 4px;
+            width: 0%;
+            transition: width 0.3s ease;
+        }
+        
+        .progress-text {
+            font-size: 14px;
+            color: #666;
+            text-align: center;
+        }
+        
+        .result-section {
+            margin-bottom: 30px;
+        }
+        
+        .result-card {
+            border: 1px solid #e0e0e0;
+            border-radius: 8px;
+            padding: 20px;
+            margin-bottom: 20px;
+            background-color: #fafafa;
+        }
+        
+        .result-card h3 {
+            color: #333;
+            margin-bottom: 15px;
+            font-size: 18px;
+            display: flex;
+            align-items: center;
+            gap: 10px;
+        }
+        
+        .result-card h3::before {
+            content: '';
+            width: 4px;
+            height: 20px;
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            border-radius: 2px;
+        }
+        
+        .result-content {
+            background-color: white;
+            border: 1px solid #e0e0e0;
+            border-radius: 6px;
+            padding: 15px;
+            min-height: 100px;
+            font-size: 16px;
+            line-height: 1.6;
+            color: #333;
+            white-space: pre-wrap;
+        }
+        
+        .copy-btn {
+            background-color: #667eea;
+            color: white;
+            border: none;
+            padding: 8px 16px;
+            border-radius: 4px;
+            font-size: 14px;
+            cursor: pointer;
+            margin-top: 10px;
+            transition: all 0.3s ease;
+        }
+        
+        .copy-btn:hover {
+            background-color: #5a6fd8;
+        }
+        
+        .status-message {
+            padding: 12px;
+            border-radius: 6px;
+            margin-bottom: 20px;
+            font-size: 14px;
+            display: none;
+        }
+        
+        .status-message.success {
+            background-color: #d4edda;
+            color: #155724;
+            border: 1px solid #c3e6cb;
+        }
+        
+        .status-message.error {
+            background-color: #f8d7da;
+            color: #721c24;
+            border: 1px solid #f5c6cb;
+        }
+        
+        @media (max-width: 768px) {
+            .container {
+                margin: 10px;
+                border-radius: 8px;
+            }
+            
+            .header {
+                padding: 20px;
+            }
+            
+            .header h1 {
+                font-size: 24px;
+            }
+            
+            .content {
+                padding: 20px;
+            }
+            
+            .upload-area {
+                padding: 30px 20px;
+            }
+            
+            .btn-group {
+                flex-direction: column;
+            }
+            
+            .btn {
+                min-width: auto;
+            }
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <div class="header">
+            <h1>🎙️ 智能音频转录与摘要服务</h1>
+            <p>上传音频文件，自动转成文字并生成摘要</p>
+        </div>
+        
+        <div class="content">
+            <div class="status-message" id="statusMessage"></div>
+            
+            <div class="upload-section">
+                <div class="upload-area" id="uploadArea">
+                    <input type="file" id="audioFile" accept="audio/*">
+                    <label for="audioFile">📁 点击选择音频文件或拖拽文件到此处</label>
+                    <div class="file-info" id="fileInfo">支持 MP3、WAV、M4A 等格式</div>
+                </div>
+            </div>
+            
+            <div class="btn-group">
+                <button class="btn btn-primary" id="transcribeBtn" disabled>🔊 仅转录</button>
+                <button class="btn btn-primary" id="processBtn" disabled>✨ 转录+摘要</button>
+            </div>
+            
+            <div class="progress-section" id="progressSection">
+                <div class="progress-bar">
+                    <div class="progress-fill" id="progressFill"></div>
+                </div>
+                <div class="progress-text" id="progressText">准备中...</div>
+            </div>
+            
+            <div class="result-section">
+                <div class="result-card">
+                    <h3>📝 转录结果</h3>
+                    <div class="result-content" id="transcriptionResult">请上传音频文件并点击转录按钮</div>
+                    <button class="copy-btn" id="copyTranscriptionBtn">📋 复制转录内容</button>
+                </div>
+                
+                <div class="result-card">
+                    <h3>📋 摘要结果</h3>
+                    <div class="result-content" id="summaryResult">请先获取转录结果</div>
+                    <button class="copy-btn" id="copySummaryBtn">📋 复制摘要内容</button>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+    <script>
+        const apiBaseUrl = 'https://caoyanyi-ai.hf.space';
+        let selectedFile = null;
+        
+        // DOM 元素
+        const uploadArea = document.getElementById('uploadArea');
+        const audioFileInput = document.getElementById('audioFile');
+        const fileInfo = document.getElementById('fileInfo');
+        const transcribeBtn = document.getElementById('transcribeBtn');
+        const processBtn = document.getElementById('processBtn');
+        const progressSection = document.getElementById('progressSection');
+        const progressFill = document.getElementById('progressFill');
+        const progressText = document.getElementById('progressText');
+        const transcriptionResult = document.getElementById('transcriptionResult');
+        const summaryResult = document.getElementById('summaryResult');
+        const copyTranscriptionBtn = document.getElementById('copyTranscriptionBtn');
+        const copySummaryBtn = document.getElementById('copySummaryBtn');
+        const statusMessage = document.getElementById('statusMessage');
+        
+        // 文件选择处理
+        audioFileInput.addEventListener('change', (e) => {
+            handleFileSelection(e.target.files[0]);
+        });
+        
+        // 拖拽处理
+        uploadArea.addEventListener('dragover', (e) => {
+            e.preventDefault();
+            uploadArea.classList.add('dragover');
+        });
+        
+        uploadArea.addEventListener('dragleave', () => {
+            uploadArea.classList.remove('dragover');
+        });
+        
+        uploadArea.addEventListener('drop', (e) => {
+            e.preventDefault();
+            uploadArea.classList.remove('dragover');
+            handleFileSelection(e.dataTransfer.files[0]);
+        });
+        
+        function handleFileSelection(file) {
+            if (file && file.type.startsWith('audio/')) {
+                selectedFile = file;
+                fileInfo.textContent = `已选择: ${file.name} (${formatFileSize(file.size)})`;
+                transcribeBtn.disabled = false;
+                processBtn.disabled = false;
+                showStatus('文件已选择，点击按钮开始处理', 'success');
+            } else {
+                showStatus('请选择有效的音频文件', 'error');
+            }
+        }
+        
+        // 按钮事件
+        transcribeBtn.addEventListener('click', () => {
+            if (selectedFile) {
+                transcribeAudio();
+            }
+        });
+        
+        processBtn.addEventListener('click', () => {
+            if (selectedFile) {
+                processAudio();
+            }
+        });
+        
+        // 复制按钮
+        copyTranscriptionBtn.addEventListener('click', () => {
+            copyToClipboard(transcriptionResult.textContent, '转录内容已复制到剪贴板');
+        });
+        
+        copySummaryBtn.addEventListener('click', () => {
+            copyToClipboard(summaryResult.textContent, '摘要内容已复制到剪贴板');
+        });
+        
+        // API调用：仅转录
+        async function transcribeAudio() {
+            setLoading(true, '正在转录音频...');
+            try {
+                const formData = new FormData();
+                formData.append('file', selectedFile);
+                
+                const response = await fetch(`${apiBaseUrl}/transcribe`, {
+                    method: 'POST',
+                    body: formData
+                });
+                
+                if (!response.ok) {
+                    throw new Error('转录失败');
+                }
+                
+                const data = await response.json();
+                transcriptionResult.textContent = data.transcription;
+                showStatus('转录完成', 'success');
+            } catch (error) {
+                showStatus(`转录失败: ${error.message}`, 'error');
+                console.error('转录错误:', error);
+            } finally {
+                setLoading(false);
+            }
+        }
+        
+        // API调用：转录+摘要
+        async function processAudio() {
+            setLoading(true, '正在处理音频...');
+            try {
+                const formData = new FormData();
+                formData.append('file', selectedFile);
+                
+                const response = await fetch(`${apiBaseUrl}/process`, {
+                    method: 'POST',
+                    body: formData
+                });
+                
+                if (!response.ok) {
+                    throw new Error('处理失败');
+                }
+                
+                const data = await response.json();
+                transcriptionResult.textContent = data.transcription;
+                summaryResult.textContent = data.summary;
+                showStatus('音频处理完成', 'success');
+            } catch (error) {
+                showStatus(`处理失败: ${error.message}`, 'error');
+                console.error('处理错误:', error);
+            } finally {
+                setLoading(false);
+            }
+        }
+        
+        // 辅助函数
+        function setLoading(isLoading, message = '') {
+            if (isLoading) {
+                progressSection.style.display = 'block';
+                progressFill.style.width = '0%';
+                progressText.textContent = message;
+                transcribeBtn.disabled = true;
+                processBtn.disabled = true;
+                
+                // 模拟进度
+                let progress = 0;
+                const interval = setInterval(() => {
+                    progress += Math.random() * 10;
+                    if (progress > 90) {
+                        clearInterval(interval);
+                    }
+                    progressFill.style.width = `${progress}%`;
+                }, 500);
+                window.loadingInterval = interval;
+            } else {
+                progressSection.style.display = 'none';
+                transcribeBtn.disabled = !selectedFile;
+                processBtn.disabled = !selectedFile;
+                if (window.loadingInterval) {
+                    clearInterval(window.loadingInterval);
+                }
+            }
+        }
+        
+        function showStatus(message, type) {
+            statusMessage.textContent = message;
+            statusMessage.className = `status-message ${type}`;
+            statusMessage.style.display = 'block';
+            
+            setTimeout(() => {
+                statusMessage.style.display = 'none';
+            }, 5000);
+        }
+        
+        function copyToClipboard(text, successMessage) {
+            navigator.clipboard.writeText(text).then(() => {
+                showStatus(successMessage, 'success');
+            }).catch(err => {
+                showStatus('复制失败', 'error');
+                console.error('复制错误:', err);
+            });
+        }
+        
+        function formatFileSize(bytes) {
+            if (bytes === 0) return '0 Bytes';
+            const k = 1024;
+            const sizes = ['Bytes', 'KB', 'MB', 'GB'];
+            const i = Math.floor(Math.log(bytes) / Math.log(k));
+            return parseFloat((bytes / Math.pow(k, i)).toFixed(2)) + ' ' + sizes[i];
+        }
+    </script>
+</body>
+</html>