Ralph Batch Transcribe

Batch transcribe all playable lectures for a course with checkpoint/resume.

When to Use

• User says /ralphtrans or "batch transcribe this course".
• User wants to transcribe an entire course in one go.

Workflow

1. Start batch transcription:

python "<SKILL_DIR>/../../scripts/look_tongji.py" batch-transcribe --course-id "<ID>"

1. The CLI:

• Loads all playable lectures for the course.
• Creates/reads batch_state.json in the workspace to track progress.
• Transcribes lectures one by one, updating state after each.
• Retries failed lectures up to --max-retries times.
• Prints a summary when all lectures are done or failed.

1. Interrupt & Resume:

• Press Ctrl+C to safely stop. State is saved.
• Re-run the same command to resume from pending lectures.

State File

batch_state.json structure:

{
  "course_id": "xxx",
  "started_at": "ISO8601",
  "updated_at": "ISO8601",
  "lectures": [
    {"sub_id": "xxx", "sub_title": "xxx", "status": "pending|done|failed", "attempts": 0, "error": null}
  ]
}

After Completion

• Run /note for each transcribed lecture to generate study notes.
• Run /wiki to rebuild and serve the course site.

Where <SKILL_DIR> Points

<SKILL_DIR> is the directory containing this SKILL.md. Shared scripts (look_tongji.py, timeline_tools.py, tongji_backend/) and references live two levels up in the repository root (<SKILL_DIR>/../../scripts/ and <SKILL_DIR>/../../references/).