Skip to content

v0.10.0 - Transcription Resumability

Choose a tag to compare

@github-actions github-actions released this 14 Feb 07:50
· 39 commits to master since this release
v0.10.0
2f6b6c5

Added

  • Transcription resumability: Pipeline now tracks per-part transcription in SQLite, enabling resumption after partial failures without re-transcribing completed parts.
  • Transcripts table: New database table stores transcription segments per audio part.
  • StateManager methods: Added store_transcript(), get_transcripts(), and get_transcribed_part_indices() methods.

Benefits

  • Saves money: If transcription fails at part 8/10, next run skips parts 1-7 and only transcribes 8-10, saving Groq/STT budget.
  • Enables re-chunking: Raw transcript storage infrastructure ready for future re-chunking without re-STT.
  • Resilient: Each part is persisted immediately after successful transcription.

Fixed

  • Timestamp alignment: Stored timestamps are now adjusted with cumulative offset to ensure correct time alignment after resume.