feat(kb-workflow): 切换为 Whisper 语音识别

- 将步骤5从 OCR 改为 Whisper 语音识别
- 更新 kb-whisper 支持自动音频转换
- 默认使用中文语言 (zh) 和 base 模型
- 更新输出格式为 {platform}_{id}.txt/.srt/.json
- 添加 FunASR 作为备用方案
This commit is contained in:
2026-02-13 09:04:27 +08:00
parent 9102a973cd
commit 29dd236bb9
7 changed files with 844 additions and 155 deletions
-5
View File
@@ -67,7 +67,6 @@ def ensure_directories(base_path: Path = None) -> Dict[str, Path]:
"metadata": base_path / "metadata",
"content": base_path / "content",
"content_downloads": base_path / "content" / "downloads",
"content_subtitles": base_path / "content" / "subtitles",
"analyzed": base_path / "analyzed",
"archive": base_path / "archive",
"archive_subscriptions": base_path / "archive" / "subscriptions",
@@ -250,7 +249,6 @@ def main():
parser.add_argument('--metadata', action='store_true', help='获取元数据目录')
parser.add_argument('--content', action='store_true', help='获取内容目录')
parser.add_argument('--content_downloads', action='store_true', help='获取主内容下载目录')
parser.add_argument('--content_subtitles', action='store_true', help='获取字幕目录')
parser.add_argument('--analyzed', action='store_true', help='获取深度分析目录')
parser.add_argument('--archive_dir', action='store_true', help='获取归档目录')
parser.add_argument('--archive_subscriptions', action='store_true', help='获取订阅信息目录')
@@ -280,9 +278,6 @@ def main():
elif args.content_downloads:
print(json.dumps({"path": str(dirs["content_downloads"])}, ensure_ascii=False, indent=2))
elif args.content_subtitles:
print(json.dumps({"path": str(dirs["content_subtitles"])}, ensure_ascii=False, indent=2))
elif args.analyzed:
print(json.dumps({"path": str(dirs["analyzed"])}, ensure_ascii=False, indent=2))