Skip to content

[Bug] Transcribe stream dropped before emitting any segments #255

Description

@camilocarrai1997

Describe the bug

The transcription is still failing

To reproduce

I just followed these steps to fix the pkg_resources error:
#253

The problem is that now I get the following error when the transcription is progressing:
Upload failed: Transcribe stream dropped before emitting any segments. Likely ASR backend failed to load — check backend log + Settings → Models.

Im using Whisper large-v3 (faster-whisper — default, cross-platform)

Expected behavior

Transcribe video

Screenshots / Logs

Image Image

Environment

  • OS: Windows 11
  • Install method: Desktop app
  • Version: 0.3.0
  • GPU: NVIDIA RTX 4070 ti Super
  • RAM: 32GB

Additional context

This error also keeps appearing:

Upload failed: No ASR backend is ready. Install WhisperX/faster-whisper/MLX Whisper or set OMNIVOICE_PRELOAD_TTS_ASR=1 before launching to use the PyTorch fallback.

This error appears when i use PyTorch Whisper (CUDA / CPU via transformers pipeline)

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions