transcriptions endpoint
#20638

Closed

mtmd, server : add Voxtral Realtime 4B support with /v1/audio/transcriptions endpoint #20638

didlawowo wants to merge 6 commits into ggml-org:master from didlawowo:feat/voxtral-realtime-clean

didlawowo requested a review 17 days ago

didlawowo requested a review from

CISC 17 days ago

github-actions added model

github-actions added examples

github-actions added python

github-actions added server

didlawowo force pushed from b268ce78 to e4612666 17 days ago

didlawowo force pushed from e4612666 to b31e2c9d 17 days ago

mtmd : add Voxtral Realtime 4B audio encoder support

1335539e

mtmd : add dual-stream transcription for Voxtral Realtime

4f740da9

server : add /v1/audio/transcriptions endpoint

5cc283bc

server : add multipart/form-data support for audio transcriptions

22843c39

fix : clean up transcription output artifacts

ae07cb26

tests : add audio transcription endpoint tests

97907d0d

didlawowo force pushed from b31e2c9d to 97907d0d 13 days ago

ngxson closed this 10 days ago

Reviewers

CISC

Assignees

No one assigned

Labels

model examples python server

Milestone

No milestone