intel / intel/openvino-plugins-ai-audacity
3.7 Transcript failure
- Dominant language
- C++
- Stars
- 2.1k
- Forks
- 135
- Avg merge
- 7d 3h
- Merged PRs (30d)
- 1
Description
Updated to 3.7 but got this trying out my test file:
`23:48:14: Open(G:\Videos\Final videos\R&B audio.wav) succeeded
23:48:17: Operation 'Importing WAV (Microsoft)' took 3.113000 seconds. Poll was called 461 times and took 0.049094 seconds. Yield was called 49 times and took 0.012405 seconds.
23:48:18: Operation 'Music Information Retrieval' took 0.000000 seconds. Poll was called 0 times and took 0.000000 seconds. Yield was called 0 times and took 0.000000 seconds.
23:48:55: Operation 'Pre-processing' took 0.000000 seconds. Poll was called 0 times and took 0.000000 seconds. Yield was called 0 times and took 0.000000 seconds.
23:49:13: Error: In Whisper Transcription Effect, exception: whisper_full_parallel failed.
23:49:19: Operation 'OpenVINO Whisper Transcription' took 17.716000 seconds. Poll was called 1945 times and took 0.095825 seconds. Yield was called 92 times and took 0.034877 seconds.
`
The file is 40 minutes. Selecting a shorter section (like a minute), all worked. "Enemy" territory as I have an AMD CPU but this file has worked on 3.5 (skipped 3.6).
Settings:
- CPU, auto (English), large-2, segment length 60, beam 10
Contributor guide
Research direction
The report identifies the Whisper Transcription Effect and OpenVINO Whisper Transcription operation; start by reproducing the failure with the supplied 40-minute WAV and settings. Compare it with a one-minute selection and the behavior in version 3.5. Done means identifying and fixing the full-length transcription failure and verifying the result with a regression test if the project provides one.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai, audio-video-rtc
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100