• Stefy Lanza (nextime / spora )'s avatar
    audio: CrisperWhisper long-form windowing + worker self-heal · b0483e8c
    Stefy Lanza (nextime / spora ) authored
    - Long-form fix: the HF pipeline's internal word-timestamp stitching crashes at
      the ~30s chunk boundary for CrisperWhisper (IndexError, dim-2 index==size). The
      service now windows manually — pipeline built without chunk_length_s; audio read
      via soundfile, split into <=28s windows (each a single Whisper pass), per-window
      word/segment timestamps offset by window start and concatenated. Verified on an
      ~11min clip: 1877 words, continuous timestamps to 673s, HTTP 200.
    - Self-heal: _RemoteCrisperWhisperBackend + _RemoteNemoBackend re-ensure the
      worker and retry once on a ConnectionError, so a restarted/killed worker no
      longer leaves a stale cached service_url in acquire_stt_backend.
    Co-Authored-By: 's avatarClaude Opus 4.8 <noreply@anthropic.com>
    Claude-Session: https://claude.ai/code/session_01R6iugoNeEgt9PkajKrFyq4
    b0483e8c
stt_backends.py 20.2 KB