Vlog Auto Edit

# 检测 whisper
python3 -c "import whisper; print('✅ whisper已安装:', whisper.__file__)"

# 检测 Pillow
python3 -c "from PIL import Image; print('✅ Pillow已安装')"

# 方案A: 直接装到用户环境（推荐）
pip install openai-whisper Pillow

# 方案B: 如果用户环境有冲突，再用 venv
python3 -m venv .venv && source .venv/bin/activate
pip install openai-whisper Pillow

python3 -c "import whisper; print('✅ whisper可用')" 2>/dev/null \
  || python3 -c "from funasr import AutoModel; print('✅ funasr可用')" 2>/dev/null \
  || echo "❌ 没有可用的ASR引擎，需要安装一个"

ffmpeg -filters 2>&1 | grep drawtext
# 有drawtext → 直接用ffmpeg，不需要Pillow
# 没有 → 用Pillow生成透明PNG再overlay（macOS brew ffmpeg通常没编freetype）

which yt-dlp && echo "✅ yt-dlp已安装" || pip install yt-dlp
python3 -c "import scenedetect" 2>/dev/null && echo "✅ scenedetect已安装" || pip install scenedetect

import base64, json, urllib.request

API_URL = 'YOUR_VISION_API_ENDPOINT'   # 替换为你的视觉模型端点
API_KEY='***'               # 替换为你的API Key
MODEL = 'YOUR_MODEL_NAME'             # 替换为你的模型名

with open('frame.jpg', 'rb') as f:
    img_b64 = base64.b64encode(f.read()).decode()

payload = {
    'model': MODEL,
    'messages': [{'role': 'user', 'content': [
        {'type': 'image_url', 'image_url': {'url': f'data:image/jpeg;base64,{img_b64}'}},
        {'type': 'text', 'text': '简洁描述画面内容，标注：镜头类型(远/全/中/近/特写)、拍摄手法(固定/手持/移动)、画面氛围。格式：内容|类型|手法|氛围'}
    ]}],
    'max_tokens': 200
}

req = urllib.request.Request(API_URL, json.dumps(payload).encode(),
    {'Content-Type': 'application/json', 'Authorization': f'Bearer {API_KEY}'})
with urllib.request.urlopen(req, timeout=30) as resp:
    result = json.loads(resp.read())
    print(result['choices'][0]['message']['content'])

# 批量获取素材信息
for f in footage/*.{MOV,mp4,MP4}; do
  echo "=== $f ==="
  ffprobe -v quiet -print_format json -show_format -show_streams "$f" \
    | python3 -c "import json,sys; d=json.load(sys.stdin); \
      s=d['streams'][0]; f=d['format']; \
      print(f\"  时长: {float(f['duration']):.1f}s\"); \
      print(f\"  分辨率: {s['width']}x{s['height']}\"); \
      print(f\"  编码: {s['codec_name']}\")"
done

# 提取音频（16kHz单声道WAV，两个引擎通用的最佳输入格式）
ffmpeg -i footage/INPUT.MOV -vn -acodec pcm_s16le -ar 16000 -ac 1 /tmp/audio.wav

import whisper, json
model = whisper.load_model('medium')
result = model.transcribe('/tmp/audio.wav', language='zh')
segments = [{"start": s['start'], "end": s['end'], "text": s['text']} for s in result['segments']]
# 输出: [{"start": 0.5, "end": 2.3, "text": "我们现在在中央大街"}, ...]

import warnings
warnings.filterwarnings("ignore")
from funasr import AutoModel

model = AutoModel(
    model="paraformer-zh",      # Paraformer-large，中文ASR主模型(1.05GB)
    vad_model="fsmn-vad",       # 语音活动检测，自动切分静音段
    punc_model="ct-punc",       # 自动加标点
    log_level="ERROR",
    disable_update=True         # 跳过版本检查，加快启动
)

result = model.generate(input="/tmp/audio.wav")
text = result[0]["text"]        # 完整识别文本（已加标点）
timestamps = result[0].get("timestamp", [])  # 字级别时间戳 [[start_ms, end_ms], ...]

# ⚠ FunASR时间戳是字级别(毫秒)，需要聚合成句级别才能和whisper格式统一
# 聚合策略：按标点符号（。！？，）切分成句子
segments = []
if timestamps and text:
    puncs = set("。！？，,.!?")
    current_start = timestamps[0][0] / 1000.0
    current_text = ""
    chars = list(text)
    for i, (char, ts) in enumerate(zip(chars, timestamps)):
        current_text += char
        if char in puncs or i == len(chars) - 1:
            segments.append({
                "start": round(current_start, 1),
                "end": round(ts[1] / 1000.0, 1),
                "text": current_text.strip()
            })
            if i < len(chars) - 1:
                current_start = timestamps[i + 1][0] / 1000.0
            current_text = ""
# 输出格式与whisper一致: [{"start": 0.6, "end": 2.9, "text": "我们现在在中央大街的入口，"}, ...]

ffmpeg -i footage/INPUT.MOV -af volumedetect -f null /dev/null 2>&1 | grep volume
# mean_volume: 平均音量(dB)  max_volume: 峰值音量(dB)
# mean < -40dB 基本无声  mean > -20dB 有明显声音/语音

# 抽帧策略（按时长分段）
# ≤20s → 3帧(首/中/尾)
# 20-60s → 5帧
# >60s → 每15s一帧

# 抽首/中/尾三帧示例（缩到720p节省带宽）
ffmpeg -i footage/INPUT.MOV -vf "select=eq(n\,0),scale=1280:-1" -frames:v 1 -q:v 2 frame_start.jpg
ffmpeg -i footage/INPUT.MOV -vf "select=eq(n\,MIDDLE),scale=1280:-1" -frames:v 1 -q:v 2 frame_mid.jpg
ffmpeg -i footage/INPUT.MOV -vf "reverse,scale=1280:-1" -frames:v 1 -q:v 2 frame_end.jpg

{
  "filename": "clip_001.MOV",
  "duration": 15.3,
  "resolution": "1920x1080",
  "visual": [
    {"time": "0:00", "description": "...", "shot_type": "近景", "camera": "手持", "mood": "温馨"}
  ],
  "audio": {
    "has_speech": true,
    "mean_volume_db": -20.5,
    "max_volume_db": -3.2,
    "transcript": [{"start": 0.5, "end": 2.3, "text": "..."}]
  }
}

RECORDING_CUES = [
    "开始了", "好了开始", "开始录了", "好了 开始",
    "走了", "好了", "来了",  # 仅在前3s内出现时算口令
]

def detect_cues(transcript_segments, duration):
    """检测录制口令，返回skip zones"""
    skip_zones = []
    for seg in transcript_segments:
        text = seg['text'].strip()
        if seg['start'] < 3.0 and any(text.startswith(c) or text == c for c in RECORDING_CUES):
            skip_zones.append({
                'type': 'recording_cue',
                'range': [seg['start'], seg['end']],
                'text': text,
                'action': 'skip'
            })
        if seg['end'] > duration - 3.0 and text in ["好了", "走了", "好了 走"]:
            skip_zones.append({
                'type': 'recording_cue',
                'range': [seg['start'], seg['end']],
                'text': text,
                'action': 'skip'
            })
    return skip_zones

from difflib import SequenceMatcher

def detect_repeats(segments, threshold=0.6):
    """检测重复语音，标记建议跳过的重复段"""
    repeats = []
    for i, a in enumerate(segments):
        for j, b in enumerate(segments):
            if j <= i: continue
            ratio = SequenceMatcher(None, a['text'], b['text']).ratio()
            if ratio >= threshold and len(a['text']) > 4:
                skip = a if len(a['text']) <= len(b['text']) else b
                repeats.append({
                    'type': 'repeat',
                    'range': [skip['start'], skip['end']],
                    'text': skip['text'],
                    'kept': b['text'] if skip == a else a['text'],
                    'action': 'suggest_skip'
                })
    return repeats

def detect_trim_points(segments, duration, mean_volume_db):
    """基于语音+音量推荐起止点"""
    suggested_start = 0.0
    suggested_end = duration

    if segments:
        first_speech = segments[0]['start']
        last_speech_end = segments[-1]['end']
        if first_speech > 2.0:
            suggested_start = max(0, first_speech - 0.5)
        if duration - last_speech_end > 3.0:
            suggested_end = last_speech_end + 1.5
    else:
        if duration > 5.0:
            suggested_start = 1.0

    return suggested_start, suggested_end

━━━ clip_012.mp4 | 时长25.8s | 1920x1080 ━━━
  【画面】...
  【语音】...
  【精修建议】模式: normal
    原始区间: [0.0 - 25.8]
    推荐区间: [2.4 - 25.8]
    ⊘ [0.0-2.4] 跳过: 录制口令 "开始了"
    有效语音: [2.62-25.8]

{
  "title": "视频标题",
  "structure": [
    {
      "section": "段落名 — 副标题",
      "description": "本段落内容概述",
      "clips": [
        {
          "file": "素材文件名.mp4",
          "start": 0.0,
          "end": 12.0,
          "note": "画面内容简述",
          "subtitle": "保留的语音文字"
        }
      ]
    }
  ],
  "bgm_suggestion": "BGM风格建议（含genre/mood/instruments/tempo/bpm）",
  "editing_notes": "整体剪辑说明"
}

# 最小用法（只生成素材面板）
python3 scripts/gen_dashboard.py \
  --analysis clip_analysis.json \
  --plan edit_plan.json \
  --footage footage/ \
  --out output/

# 完整两面板（含成品QC帧）
python3 scripts/gen_dashboard.py \
  --analysis clip_analysis.json \
  --plan edit_plan.json \
  --footage footage/ \
  --video output/final.mp4 \
  --out output/

def validate_speech(plan_clips, speech_data):
    """检查每个clip的start/end是否截断了语音"""
    issues = []
    for clip in plan_clips:
        f = clip['file']
        cs, ce = clip['start'], clip['end']
        if f not in speech_data: continue
        for ss, se, txt in speech_data[f]:
            if ss < ce and se > cs:  # 语音与clip有交集
                if ss < cs - 0.3:    # 语音开始在clip之前
                    issues.append(f"截断开头: {f} clip从{cs}开始，但语音\"{txt}\"从{ss}开始")
                if se > ce + 0.5:    # 语音结束在clip之后
                    issues.append(f"截断结尾: {f} clip在{ce}结束，但语音\"{txt}\"到{se}结束")
    return issues

def fix_speech_cuts(plan, speech_data, margin=0.3):
    """
    自动修复语音截断问题。直接修改plan中的start/end。
    
    参数:
        plan: edit_plan dict (会被原地修改)
        speech_data: dict, {filename: [(start, end, text), ...]}
        margin: float, 语音边界容差(秒)
    
    返回:
        fixes: list of str, 修复日志
    """
    fixes = []
    
    for sec in plan["structure"]:
        for clip in sec["clips"]:
            f = clip["file"]
            cs = float(clip["start"])
            ce = float(clip["end"])
            
            if f not in speech_data:
                continue
            
            for ss, se, txt in speech_data[f]:
                if ss >= ce or se <= cs:
                    continue
                
                # 开头截断：clip.start > speech.start + margin
                if ss < cs - margin and se > cs:
                    old_start = cs
                    new_start = max(0, ss - 0.1)
                    clip["start"] = round(new_start, 1)
                    fixes.append(
                        f"  修复开头: {f} [{old_start}→{new_start}] "
                        f"语音\"{txt[:20]}\"从{ss}s开始"
                    )
                    cs = new_start
                
                # 结尾截断：clip.end < speech.end - margin
                if se > ce + margin and ss < ce:
                    old_end = ce
                    new_end = se + 0.2
                    clip["end"] = round(new_end, 1)
                    fixes.append(
                        f"  修复结尾: {f} [{old_end}→{new_end}] "
                        f"语音\"{txt[:20]}\"到{se}s结束"
                    )
                    ce = new_end
    
    return fixes


def validate_and_fix(plan, speech_data):
    """
    端到端校验+修复入口。
    
    用法:
        import json
        # 加载plan
        plan = json.load(open('edit_plan.json'))
        # 加载语音数据 (格式: {filename: [{start, end, text}, ...]})
        raw = json.load(open('clip_analysis.json'))
        speech_data = {}
        for clip_info in raw:
            fname = clip_info['filename']
            if clip_info['audio']['has_speech']:
                speech_data[fname] = [
                    (s['start'], s['end'], s['text'])
                    for s in clip_info['audio']['transcript']
                ]
        
        # 校验
        all_clips = [c for sec in plan['structure'] for c in sec['clips']]
        issues = validate_speech(all_clips, speech_data)
        print(f'发现 {len(issues)} 个截断问题')
        
        # 修复
        fixes = fix_speech_cuts(plan, speech_data)
        print(f'自动修复 {len(fixes)} 处')
        
        # 二次校验确认
        all_clips2 = [c for sec in plan['structure'] for c in sec['clips']]
        issues2 = validate_speech(all_clips2, speech_data)
        assert len(issues2) == 0, f'仍有 {len(issues2)} 个问题未修复!'
        print('✅ 二次校验通过')
        
        # 保存修复后的plan
        json.dump(plan, open('edit_plan_fixed.json', 'w', ensure_ascii=False), indent=2)
    """
    all_clips = [c for sec in plan['structure'] for c in sec['clips']]
    issues = validate_speech(all_clips, speech_data)
    fixes = fix_speech_cuts(plan, speech_data)
    return issues, fixes

# 单个片段裁剪+编码
ffmpeg -y -ss 00:00:02.400 -i footage/INPUT.mp4 -t 00:00:23.400 \
  -vf "scale=1920:1080:force_original_aspect_ratio=decrease,pad=1920:1080:(ow-iw)/2:(oh-ih)/2,setsar=1" \
  -r 30 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p \
  -c:a aac -b:a 128k -ar 44100 -ac 2 \
  -movflags +faststart segments/seg_001.mp4

# 拼接成品
ffmpeg -y -f concat -safe 0 -i concat.txt -c copy -movflags +faststart output.mp4

# 2倍速（视频+音频同步）
ffmpeg -i input.mp4 -filter:v "setpts=0.5*PTS" -filter:a "atempo=2.0" out.mp4

import subprocess, os

highlights = [
    ('footage/clip_a.mp4',   1.5, 2.2),
    ('footage/clip_b.mp4',   2.0, 2.7),
    # ... 每个0.7秒左右
]

for i, (f, start, end) in enumerate(highlights, 1):
    dur = end - start
    cmd = f'ffmpeg -y -ss {start} -i "{f}" -t {dur} ' \
          f'-vf "scale=1920:1080:force_original_aspect_ratio=decrease,' \
          f'pad=1920:1080:(ow-iw)/2:(oh-ih)/2" ' \
          f'-c:v libx264 -preset ultrafast -crf 23 -pix_fmt yuv420p ' \
          f'-an highlights/hl_{i}.mp4'
    subprocess.run(cmd, shell=True)

# concat
with open('highlights/concat.txt', 'w') as f:
    for i in range(1, len(highlights)+1):
        f.write(f"file 'hl_{i}.mp4'\n")

subprocess.run('ffmpeg -y -f concat -safe 0 -i highlights/concat.txt '
               '-c copy highlights/montage.mp4', shell=True)