fix(whisper): convert non-WAV audio to WAV for Open WebUI compatibility#2481
Draft
vgodsoe wants to merge 8 commits into
Draft
fix(whisper): convert non-WAV audio to WAV for Open WebUI compatibility#2481vgodsoe wants to merge 8 commits into
vgodsoe wants to merge 8 commits into
Conversation
…er-server Open WebUI records audio as WebM/Opus, which whisper.cpp cannot process natively. WhisperServer now calls ffmpeg to convert any non-WAV input to 16 kHz mono WAV before forwarding to the subprocess, fixing the 500 error users see with Open WebUI. Co-Authored-By: Claude <noreply@anthropic.com>
github-actions
Bot
added
engine::whispercpp
fs::remove() fails with access-denied on open handles on Windows, causing temp WAV files to accumulate in temp_dir_ for the server lifetime. Co-Authored-By: Claude <noreply@anthropic.com>
…te forwarding logic Co-Authored-By: Claude <noreply@anthropic.com>
…rrent requests Co-Authored-By: Claude <noreply@anthropic.com>
…t policy of HTTP POST Large WebM files on slow machines can exceed 30 s to transcode; -1 matches the same no-cap approach used for the whisper-server inference POST. Co-Authored-By: Claude <noreply@anthropic.com>
…sion is not skipped audio.wav caused send_audio_to_whisper to bypass the ext != .wav conversion guard, forwarding raw WebM/Opus bytes to whisper-server labeled as WAV. Co-Authored-By: Claude <noreply@anthropic.com>
Contributor
Author
|
@copilot resolve the merge conflicts in this pull request |
…ersion # Conflicts: # src/cpp/server/backends/whispercpp/whispercpp_server.cpp
Contributor
Merge conflicts resolved in 8d262a6. The conflict was in |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
WhisperServernow calls ffmpeg to convert any non-WAV input to 16 kHz mono WAV before forwarding to the subprocessforward_multipart_audio_data(used by the main transcription path) andforward_multipart_audio_request(file-path variant) are fixed consistentlyTest plan
curl -X POST http://localhost:13305/v1/audio/transcriptions -F "file=@test.webm" -F "model=Whisper-Tiny"returns transcriptpython test/server_whisper.py🤖 Generated with Claude Code