manifest.json里extract audio, transcribe audio 共用一条记录

synthmind/transcribe_audio.py

@@ -66,13 +66,38 @@ def log(msg: str, level: str = "INFO"):
     print(f"[{ts}] {prefix} {msg}", flush=True)
 
 
-# ─── Manifest 操作 (key 包含 model，支持同一音频多模型共存) ────────────────────
+# ─── Manifest 操作 (v2 schema) ────────────────────────────────────────────────
+#
+# v2 schema：每条记录以 视频路径 (extract_audio 流) 或 音频路径 (独立转录) 为 key，
+# 包含 extraction + transcriptions 两部分。extract_audio 与 transcribe_audio
+# 共写同一条记录，互不覆盖。
+#
+# {
+#   "<key>": {
+#     "extraction": { "extracted": bool, "audio_path": str, "split_segments": [],
+#                     "error": str|None, "updated_at": str } | null,
+#     "transcriptions": {
+#       "<model>[:<suffix>]": { "transcribed": bool, "txt_path": str, "model": str,
+#                               "language": str|None, "output_suffix": str|None,
+#                               "split_segments": [], "error": str|None,
+#                               "updated_at": str }
+#     }
+#   }
+# }
+# ─────────────────────────────────────────────────────────────────────────────
+
+MANIFEST_VERSION = 2
+
 
 def load_manifest(manifest_path: Path) -> dict:
-    if manifest_path.exists():
-        with open(manifest_path, encoding="utf-8") as f:
-            return json.load(f)
-    return {"version": 1, "files": {}}
+    if not manifest_path.exists():
+        return {"version": MANIFEST_VERSION, "files": {}}
+    with open(manifest_path, encoding="utf-8") as f:
+        data = json.load(f)
+    if data.get("version", 1) < MANIFEST_VERSION:
+        log("检测到旧版 manifest.json (v1)，将以 v2 schema 重新初始化 - 旧记录将被覆盖", "WARN")
+        return {"version": MANIFEST_VERSION, "files": {}}
+    return data
 
 
 def save_manifest(manifest_path: Path, manifest: dict):
@@ -81,31 +106,56 @@ def save_manifest(manifest_path: Path, manifest: dict):
         json.dump(manifest, f, ensure_ascii=False, indent=2)
 
 
-def transcribe_key(model: str, audio_path: str, output_suffix: str = "") -> str:
-    """
-    manifest key 由 model + output_suffix + 音频路径共同决定，
-    因此改变 --output-suffix 会形成新的 key（不会误跳过）。
-    """
+def transcription_subkey(model: str, output_suffix: str = "") -> str:
+    """transcriptions 字典的 subkey：<model> 或 <model>:<suffix>"""
     if output_suffix:
-        return f"transcribe:{model}:{output_suffix}:{audio_path}"
-    return f"transcribe:{model}:{audio_path}"
+        return f"{model}:{output_suffix}"
+    return model
+
+
+def find_entry_key_for_audio(manifest: dict, audio_path: str) -> str:
+    """
+    反向查找：audio 属于哪条 manifest 记录。
+    - 若某视频记录的 extraction.audio_path == audio → 归入该视频 key
+    - 否则以 audio_path 自身为 key（独立音频场景）
+    """
+    for key, entry in manifest["files"].items():
+        extraction = entry.get("extraction")
+        if extraction and extraction.get("audio_path") == audio_path:
+            return key
+    return audio_path
+
+
+def ensure_entry(manifest: dict, key: str) -> dict:
+    if key not in manifest["files"]:
+        manifest["files"][key] = {
+            "extraction": None,
+            "transcriptions": {},
+        }
+    entry = manifest["files"][key]
+    if "transcriptions" not in entry:
+        entry["transcriptions"] = {}
+    return entry
 
 
 def get_transcribe_entry(manifest: dict, audio_path: str, model: str,
                          output_suffix: str = "") -> dict:
-    key = transcribe_key(model, audio_path, output_suffix)
-    if key not in manifest["files"]:
-        manifest["files"][key] = {
+    """获取或初始化某个 (音频, 模型, suffix) 的转录记录"""
+    key = find_entry_key_for_audio(manifest, audio_path)
+    parent = ensure_entry(manifest, key)
+    subkey = transcription_subkey(model, output_suffix)
+    if subkey not in parent["transcriptions"]:
+        parent["transcriptions"][subkey] = {
             "transcribed": False,
             "txt_path": None,
             "split_segments": [],
-            "error": None,
             "model": model,
             "language": None,
             "output_suffix": output_suffix or None,
+            "error": None,
             "updated_at": None,
         }
-    return manifest["files"][key]
+    return parent["transcriptions"][subkey]
 
 
 def mark_transcribed(manifest: dict, manifest_path: Path, audio_path: str,
@@ -305,31 +355,43 @@ def show_status(manifest: dict, all_audios: list):
     print("📊 音频转录进度状态（按 模型 x 音频 展示）")
     print("=" * 70)
 
-    entries = {k: v for k, v in manifest["files"].items() if k.startswith("transcribe:")}
-    done = sum(1 for v in entries.values() if v.get("transcribed"))
-    failed = sum(1 for v in entries.values() if v.get("error"))
-    print(f"  Manifest 记录: {len(entries)}  已完成: {done}  失败: {failed}")
+    all_trans = []
+    for parent_key, entry in manifest["files"].items():
+        for subkey, tr in (entry.get("transcriptions") or {}).items():
+            all_trans.append((parent_key, subkey, tr))
+
+    done = sum(1 for _, _, v in all_trans if v.get("transcribed"))
+    failed = sum(1 for _, _, v in all_trans if v.get("error"))
+    print(f"  转录记录: {len(all_trans)}  已完成: {done}  失败: {failed}")
     print("=" * 70)
 
     for a in all_audios:
         print(f"\n  📄 {Path(a).name}")
-        matching = [(k, v) for k, v in entries.items() if k.endswith(f":{a}")]
+        matching = []
+        for parent_key, entry in manifest["files"].items():
+            extraction = entry.get("extraction") or {}
+            is_match = extraction.get("audio_path") == a or parent_key == a
+            if not is_match:
+                continue
+            for subkey, tr in (entry.get("transcriptions") or {}).items():
+                matching.append((subkey, tr))
+
         if not matching:
             print(f"     ⏳ 无记录（未转录）")
             continue
-        for key, entry in matching:
-            m = entry.get("model", "?")
-            suffix = entry.get("output_suffix") or ""
+        for subkey, tr in matching:
+            m = tr.get("model", "?")
+            suffix = tr.get("output_suffix") or ""
             suffix_tag = f" suffix={suffix}" if suffix else ""
-            if entry.get("transcribed"):
+            if tr.get("transcribed"):
                 size = ""
-                if entry.get("txt_path") and os.path.exists(entry["txt_path"]):
-                    size = f"  {os.path.getsize(entry['txt_path']) // 1024}KB"
-                lang = entry.get("language") or "auto"
-                txt_name = Path(entry['txt_path']).name if entry.get('txt_path') else '?'
+                if tr.get("txt_path") and os.path.exists(tr["txt_path"]):
+                    size = f"  {os.path.getsize(tr['txt_path']) // 1024}KB"
+                lang = tr.get("language") or "auto"
+                txt_name = Path(tr['txt_path']).name if tr.get('txt_path') else '?'
                 print(f"     ✅ [{m:6s}] lang={lang}{suffix_tag}{size}  → {txt_name}")
-            elif entry.get("error"):
-                print(f"     ❌ [{m:6s}]{suffix_tag} {entry['error'][:60]}")
+            elif tr.get("error"):
+                print(f"     ❌ [{m:6s}]{suffix_tag} {tr['error'][:60]}")
     print()