feat: VRSub 单体应用（WOV 单机版）初始提交

为视频生成 VR 双眼字幕的单体实现：FastAPI 后端、调度器与全部节点（提音/转写/翻译/ASS/抽帧/OCR/LLM 过滤）在单进程内运行。 - 节点协议（wov_sdk 数据模型）与分布式版保持一致，预留回退桥梁 - 工作流即数据：DAG 存于 workflows/*.json，模型/链路改动只改数据 - 调度器：拓扑顺序执行、断点续跑（产物重建）、任务暂停/继续 - 抽帧按帧间隔（select 按帧号精确取帧），VLM OCR 与 LLM 过滤使用自适应线程池弹性并发，并打印数据处理速度进度日志 - 100% 行覆盖率（pytest --cov-fail-under=100）
2026-08-16 23:58:25 +08:00
commit 4746e0363f
75 changed files with 10969 additions and 0 deletions
@@ -0,0 +1,78 @@
+{
+  "id": "demo",
+  "name": "视频字幕生成",
+  "description": "上传视频，自动生成中文字幕和 VR 双眼 ASS。",
+  "version": 1,
+  "definition": {
+    "name": "视频字幕生成",
+    "version": 1,
+    "nodes": [
+      {
+        "id": "extract",
+        "node_type": "ffmpeg-extract",
+        "params": {
+          "sample_rate": 16000,
+          "channels": 1
+        },
+        "inputs": {
+          "video_uri": "input.video_uri"
+        }
+      },
+      {
+        "id": "asr",
+        "node_type": "faster-whisper",
+        "params": {
+          "language": "ja",
+          "model_path": "faster-whisper-large-v3",
+          "condition_on_previous_text": false,
+          "chunk_seconds": 60,
+          "vad_filter": true
+        },
+        "inputs": {
+          "audio_uri": "extract.audio_uri"
+        }
+      },
+      {
+        "id": "translate",
+        "node_type": "llm-translate",
+        "params": {
+          "target_language": "zh-CN"
+        },
+        "inputs": {
+          "srt_uri": "asr.srt_uri"
+        }
+      },
+      {
+        "id": "ass",
+        "node_type": "srt-to-dual-eye-ass",
+        "params": {
+          "resolution": "3840x1920"
+        },
+        "inputs": {
+          "cn_srt_uri": "translate.cn_srt_uri"
+        }
+      }
+    ],
+    "edges": [
+      {
+        "from": "extract",
+        "to": "asr"
+      },
+      {
+        "from": "asr",
+        "to": "translate"
+      },
+      {
+        "from": "translate",
+        "to": "ass"
+      }
+    ],
+    "entry_inputs": {
+      "video_uri": "file"
+    },
+    "final_outputs": {
+      "cn_srt": "translate.cn_srt_uri",
+      "ass": "ass.ass_uri"
+    }
+  }
+}
@@ -0,0 +1,62 @@
+{
+  "id": "ocr-subtitle",
+  "name": "字幕OCR提取",
+  "description": "抽帧并 OCR 提取视频烧录字幕，经 LLM 过滤无意义内容后生成带时间轴的 SRT 基准数据。",
+  "version": 3,
+  "definition": {
+    "name": "字幕OCR提取",
+    "version": 3,
+    "nodes": [
+      {
+        "id": "extract",
+        "node_type": "frame-extract",
+        "params": {
+          "interval_seconds": 0.5,
+          "crop": [
+            0,
+            0.82,
+            1,
+            0.18
+          ]
+        },
+        "inputs": {
+          "video_uri": "input.video_uri"
+        }
+      },
+      {
+        "id": "ocr",
+        "node_type": "subtitle-ocr",
+        "params": {
+          "prompt": "提取图像中的文字，不要描述图片中的内容"
+        },
+        "inputs": {
+          "frames_manifest": "extract.frames_manifest"
+        }
+      },
+      {
+        "id": "filter",
+        "node_type": "llm-filter",
+        "params": {},
+        "inputs": {
+          "srt_uri": "ocr.srt_uri"
+        }
+      }
+    ],
+    "edges": [
+      {
+        "from": "extract",
+        "to": "ocr"
+      },
+      {
+        "from": "ocr",
+        "to": "filter"
+      }
+    ],
+    "entry_inputs": {
+      "video_uri": "file"
+    },
+    "final_outputs": {
+      "srt": "filter.srt_uri"
+    }
+  }
+}
@@ -0,0 +1,66 @@
+{
+  "id": "zh-direct",
+  "name": "中文直出字幕",
+  "description": "使用中文直出模型直接生成中文字幕和 VR 双眼 ASS，无需 LLM 翻译。",
+  "version": 1,
+  "definition": {
+    "name": "中文直出字幕",
+    "version": 1,
+    "nodes": [
+      {
+        "id": "extract",
+        "node_type": "ffmpeg-extract",
+        "params": {
+          "sample_rate": 16000,
+          "channels": 1
+        },
+        "inputs": {
+          "video_uri": "input.video_uri"
+        }
+      },
+      {
+        "id": "asr",
+        "node_type": "faster-whisper",
+        "params": {
+          "language": "ja",
+          "task": "translate",
+          "model_path": "whisper-large-v2-translate-zh-v0.2-st-ct2",
+          "target_language": "zh-CN",
+          "condition_on_previous_text": false,
+          "chunk_seconds": 60,
+          "vad_filter": true
+        },
+        "inputs": {
+          "audio_uri": "extract.audio_uri"
+        }
+      },
+      {
+        "id": "ass",
+        "node_type": "srt-to-dual-eye-ass",
+        "params": {
+          "resolution": "3840x1920"
+        },
+        "inputs": {
+          "cn_srt_uri": "asr.srt_uri"
+        }
+      }
+    ],
+    "edges": [
+      {
+        "from": "extract",
+        "to": "asr"
+      },
+      {
+        "from": "asr",
+        "to": "ass"
+      }
+    ],
+    "entry_inputs": {
+      "video_uri": "file"
+    },
+    "final_outputs": {
+      "cn_srt": "asr.srt_uri",
+      "ass": "ass.ass_uri"
+    }
+  }
+}