simonkoson
7eb6511169
- deploy/cca_route.py: Flask 蓝图（6个API端点），WAV自动转MP3 - deploy/cca.html: 4步单页流程（上传→处理→审稿→下载），查找替换(Ctrl+H) - src/term_normalizer.py: 新增正则层（同音字/引号/书名号/小数点/波浪号） - src/ai_proofreader.py: speaker角色识别+专家段增强Prompt+的地得加强 - src/ai_line_breaker.py: 引号不跨屏+极短行合并+短句合并间隔放宽 - cca_pipeline.py: Step 2.5 校对后二次正则兜底 - 已部署至 http://101.42.29.217/cca.html Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
331 lines
11 KiB
Python
331 lines
11 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""
|
||
CCA 唱词助手 — Flask 路由
|
||
POST /api/cca/upload 上传 A稿+音频，启动流水线
|
||
GET /api/cca/status/<id> 轮询任务状态
|
||
GET /api/cca/review/<id> 获取审稿数据
|
||
POST /api/cca/save/<id> 保存编导修改
|
||
POST /api/cca/generate/<id> 生成最终 SRT
|
||
GET /api/cca/download/<id> 下载 SRT zip
|
||
"""
|
||
|
||
import json
|
||
import os
|
||
import sys
|
||
import uuid
|
||
import threading
|
||
import traceback
|
||
import zipfile
|
||
from io import BytesIO
|
||
from pathlib import Path
|
||
from datetime import datetime
|
||
|
||
from flask import Blueprint, request, jsonify, send_file
|
||
|
||
bp = Blueprint('cca', __name__, url_prefix='/api/cca')
|
||
|
||
# 运行时数据目录
|
||
CCA_DATA_DIR = Path('/workspace/military_tech_voice/backend/cca_data')
|
||
CCA_DATA_DIR.mkdir(parents=True, exist_ok=True)
|
||
|
||
# CCA 源码目录
|
||
CCA_SRC_DIR = Path('/workspace/military_tech_voice/backend/cca_src')
|
||
if str(CCA_SRC_DIR) not in sys.path:
|
||
sys.path.insert(0, str(CCA_SRC_DIR))
|
||
|
||
# 任务状态存储（内存，重启丢失无所谓——编导重新上传即可）
|
||
tasks = {}
|
||
|
||
|
||
def _get_task(task_id):
|
||
t = tasks.get(task_id)
|
||
if not t:
|
||
return None
|
||
return t
|
||
|
||
|
||
@bp.route('/upload', methods=['POST'])
|
||
def upload():
|
||
"""接收 A稿 + 音频，创建任务"""
|
||
if 'audio' not in request.files:
|
||
return jsonify({'error': '请上传音频文件'}), 400
|
||
|
||
audio_file = request.files['audio']
|
||
script_file = request.files.get('script')
|
||
|
||
if not audio_file.filename:
|
||
return jsonify({'error': '音频文件为空'}), 400
|
||
|
||
task_id = datetime.now().strftime('%Y%m%d_%H%M%S') + '_' + uuid.uuid4().hex[:6]
|
||
task_dir = CCA_DATA_DIR / task_id
|
||
task_dir.mkdir(parents=True, exist_ok=True)
|
||
|
||
# 保存音频
|
||
audio_ext = os.path.splitext(audio_file.filename)[1] or '.mp3'
|
||
audio_path = task_dir / f'audio{audio_ext}'
|
||
audio_file.save(str(audio_path))
|
||
|
||
# 保存 A稿
|
||
script_path = None
|
||
if script_file and script_file.filename:
|
||
script_ext = os.path.splitext(script_file.filename)[1] or '.docx'
|
||
script_path = task_dir / f'script{script_ext}'
|
||
script_file.save(str(script_path))
|
||
|
||
tasks[task_id] = {
|
||
'id': task_id,
|
||
'status': 'uploaded',
|
||
'progress': '文件已上传，准备处理...',
|
||
'audio_path': str(audio_path),
|
||
'script_path': str(script_path) if script_path else None,
|
||
'created_at': datetime.now().isoformat(),
|
||
'error': None,
|
||
'asr_sentences': None,
|
||
'proofread_sentences': None,
|
||
'review_data': None,
|
||
'final_srt_dir': None,
|
||
}
|
||
|
||
# 启动后台处理
|
||
thread = threading.Thread(target=_run_pipeline, args=(task_id,), daemon=True)
|
||
thread.start()
|
||
|
||
return jsonify({'task_id': task_id, 'status': 'processing'})
|
||
|
||
|
||
def _run_pipeline(task_id):
|
||
"""后台运行 CCA 流水线"""
|
||
task = tasks[task_id]
|
||
try:
|
||
task['status'] = 'processing'
|
||
task['progress'] = '正在提取热词...'
|
||
|
||
audio_path = task['audio_path']
|
||
script_path = task['script_path']
|
||
|
||
# WAV/大文件 → MP3 压缩（讯飞上传大文件容易超时）
|
||
if audio_path.lower().endswith('.wav'):
|
||
import subprocess
|
||
mp3_path = audio_path.rsplit('.', 1)[0] + '.mp3'
|
||
task['progress'] = '正在压缩音频（WAV→MP3）...'
|
||
subprocess.run(
|
||
['ffmpeg', '-i', audio_path, '-b:a', '128k', '-y', mp3_path],
|
||
capture_output=True, timeout=300,
|
||
)
|
||
if os.path.exists(mp3_path) and os.path.getsize(mp3_path) > 0:
|
||
audio_path = mp3_path
|
||
task['audio_path'] = mp3_path
|
||
|
||
from hotword_extractor import extract_hotwords, read_docx_text, read_text_file
|
||
from asr_client import transcribe, parse_result
|
||
from term_normalizer import normalize_terms
|
||
from ai_proofreader import proofread_batch
|
||
from segment_splitter import split_into_segments
|
||
|
||
# Step 0: 热词提取
|
||
hot_words = []
|
||
script_text = ""
|
||
if script_path:
|
||
hot_words = extract_hotwords(script_path, use_ai=True)
|
||
ext = os.path.splitext(script_path)[1].lower()
|
||
if ext == '.docx':
|
||
script_text = read_docx_text(script_path)
|
||
else:
|
||
script_text = read_text_file(script_path)
|
||
|
||
task['progress'] = f'热词提取完成({len(hot_words)}个)，正在 ASR 转写...'
|
||
|
||
# Step 1: ASR
|
||
sentences, raw_json = transcribe(audio_path, hot_words=hot_words if hot_words else None)
|
||
|
||
# 缓存 ASR 原始结果
|
||
task_dir = Path(audio_path).parent
|
||
cache_path = task_dir / 'asr_raw.json'
|
||
with open(cache_path, 'w', encoding='utf-8') as f:
|
||
f.write(raw_json)
|
||
|
||
task['progress'] = f'ASR 完成({len(sentences)}句)，正在术语格式化...'
|
||
|
||
# 保存 ASR 原始句子（校对前，供 diff 对比）
|
||
asr_original = [(bg, ed, text, spk) for bg, ed, text, spk in sentences]
|
||
|
||
# Step 1.5: 术语格式化
|
||
if script_text:
|
||
sentences = normalize_terms(sentences, script_text)
|
||
|
||
task['progress'] = '术语格式化完成，正在 AI 校对...'
|
||
|
||
# Step 2: AI 校对
|
||
if script_text:
|
||
sentences = proofread_batch(sentences, script_text)
|
||
|
||
# Step 2.5: 校对后二次正则
|
||
if script_text:
|
||
sentences = normalize_terms(sentences, script_text)
|
||
|
||
task['progress'] = 'AI 校对完成，正在准备审稿数据...'
|
||
|
||
# 保存校对后的句子
|
||
task['asr_sentences'] = asr_original
|
||
task['proofread_sentences'] = sentences
|
||
|
||
# 构建审稿数据：逐句对比
|
||
review_items = []
|
||
for i, ((bg, ed, orig_text, spk), (_, _, proof_text, _)) in enumerate(
|
||
zip(asr_original, sentences)
|
||
):
|
||
has_change = orig_text != proof_text
|
||
review_items.append({
|
||
'index': i,
|
||
'start_ms': bg,
|
||
'end_ms': ed,
|
||
'speaker_id': spk,
|
||
'original': orig_text,
|
||
'corrected': proof_text,
|
||
'edited': proof_text,
|
||
'has_change': has_change,
|
||
'confirmed': not has_change,
|
||
})
|
||
|
||
task['review_data'] = review_items
|
||
task['status'] = 'review'
|
||
task['progress'] = '审稿数据就绪，请编导审阅确认'
|
||
|
||
# 同时保存到磁盘（防丢）
|
||
review_path = task_dir / 'review_data.json'
|
||
with open(review_path, 'w', encoding='utf-8') as f:
|
||
json.dump(review_items, f, ensure_ascii=False, indent=2)
|
||
|
||
except Exception as e:
|
||
task['status'] = 'error'
|
||
err_msg = str(e)
|
||
if '余额不足' in err_msg or 'insufficient' in err_msg.lower() or '10317' in err_msg:
|
||
task['error'] = '讯飞录音文件转写余额不足，请联系管理员充值'
|
||
else:
|
||
task['error'] = f'处理出错: {err_msg}'
|
||
task['progress'] = task['error']
|
||
traceback.print_exc()
|
||
|
||
|
||
@bp.route('/status/<task_id>', methods=['GET'])
|
||
def status(task_id):
|
||
task = _get_task(task_id)
|
||
if not task:
|
||
return jsonify({'error': '任务不存在'}), 404
|
||
return jsonify({
|
||
'task_id': task_id,
|
||
'status': task['status'],
|
||
'progress': task['progress'],
|
||
'error': task['error'],
|
||
})
|
||
|
||
|
||
@bp.route('/review/<task_id>', methods=['GET'])
|
||
def review(task_id):
|
||
task = _get_task(task_id)
|
||
if not task:
|
||
return jsonify({'error': '任务不存在'}), 404
|
||
if task['status'] not in ('review', 'completed'):
|
||
return jsonify({'error': '任务尚未就绪', 'status': task['status']}), 400
|
||
return jsonify({
|
||
'task_id': task_id,
|
||
'items': task['review_data'],
|
||
})
|
||
|
||
|
||
@bp.route('/save/<task_id>', methods=['POST'])
|
||
def save(task_id):
|
||
"""保存编导的修改（自动保存用）"""
|
||
task = _get_task(task_id)
|
||
if not task:
|
||
return jsonify({'error': '任务不存在'}), 404
|
||
|
||
data = request.get_json()
|
||
edits = data.get('items', [])
|
||
|
||
for edit in edits:
|
||
idx = edit.get('index')
|
||
if idx is not None and 0 <= idx < len(task['review_data']):
|
||
task['review_data'][idx]['edited'] = edit.get('edited', task['review_data'][idx]['edited'])
|
||
task['review_data'][idx]['confirmed'] = edit.get('confirmed', True)
|
||
|
||
return jsonify({'ok': True})
|
||
|
||
|
||
@bp.route('/generate/<task_id>', methods=['POST'])
|
||
def generate(task_id):
|
||
"""用编导确认后的文本生成最终 SRT"""
|
||
task = _get_task(task_id)
|
||
if not task:
|
||
return jsonify({'error': '任务不存在'}), 404
|
||
if task['status'] not in ('review', 'completed'):
|
||
return jsonify({'error': '任务状态不对'}), 400
|
||
|
||
try:
|
||
from ai_line_breaker import process_sentences_with_ai
|
||
from srt_writer import write_srt, ms_to_srt_time
|
||
from segment_splitter import split_into_segments
|
||
|
||
# 用编导确认后的文本重建句子列表
|
||
confirmed_sentences = []
|
||
for item in task['review_data']:
|
||
text = item['edited']
|
||
confirmed_sentences.append((
|
||
item['start_ms'], item['end_ms'], text, item['speaker_id']
|
||
))
|
||
|
||
# 切分节目结构
|
||
segments = split_into_segments(confirmed_sentences)
|
||
|
||
# 折行 + 生成 SRT
|
||
task_dir = Path(task['audio_path']).parent
|
||
srt_dir = task_dir / 'srt_output'
|
||
srt_dir.mkdir(exist_ok=True)
|
||
|
||
srt_files = []
|
||
for seg_name, seg_sentences in segments:
|
||
if not seg_sentences:
|
||
continue
|
||
subtitle_lines = process_sentences_with_ai(seg_sentences)
|
||
srt_path = srt_dir / f'{seg_name}.srt'
|
||
write_srt(subtitle_lines, str(srt_path))
|
||
srt_files.append(str(srt_path))
|
||
|
||
task['final_srt_dir'] = str(srt_dir)
|
||
task['status'] = 'completed'
|
||
task['progress'] = f'生成完成，共 {len(srt_files)} 个 SRT 文件'
|
||
|
||
return jsonify({
|
||
'ok': True,
|
||
'srt_count': len(srt_files),
|
||
'message': task['progress'],
|
||
})
|
||
|
||
except Exception as e:
|
||
return jsonify({'error': f'生成 SRT 出错: {str(e)}'}), 500
|
||
|
||
|
||
@bp.route('/download/<task_id>', methods=['GET'])
|
||
def download(task_id):
|
||
"""下载 SRT zip 包"""
|
||
task = _get_task(task_id)
|
||
if not task:
|
||
return jsonify({'error': '任务不存在'}), 404
|
||
if not task.get('final_srt_dir'):
|
||
return jsonify({'error': 'SRT 尚未生成'}), 400
|
||
|
||
srt_dir = Path(task['final_srt_dir'])
|
||
srt_files = sorted(srt_dir.glob('*.srt'))
|
||
if not srt_files:
|
||
return jsonify({'error': '无 SRT 文件'}), 404
|
||
|
||
# 打包 zip
|
||
buf = BytesIO()
|
||
with zipfile.ZipFile(buf, 'w', zipfile.ZIP_DEFLATED) as zf:
|
||
for srt_file in srt_files:
|
||
zf.write(srt_file, srt_file.name)
|
||
buf.seek(0)
|
||
|
||
filename = f'唱词字幕_{task_id}.zip'
|
||
return send_file(buf, mimetype='application/zip', as_attachment=True, download_name=filename)
|