RD-623: Argmax OSS engine and pipelines (replace legacy WhisperKit transcription)#99
Open
EduardoPach wants to merge 1 commit intomainfrom
Open
RD-623: Argmax OSS engine and pipelines (replace legacy WhisperKit transcription)#99EduardoPach wants to merge 1 commit intomainfrom
EduardoPach wants to merge 1 commit intomainfrom
Conversation
Introduce argmax_oss_engine and wire transcription, diarization, and orchestration pipelines plus pipeline aliases. Remove legacy whisperkit transcription module in favor of Argmax OSS. Made-with: Cursor
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
This change integrates the Argmax open-source Swift CLI (
argmax-clifrom argmaxinc/argmax-oss-swift) into OpenBench as a first-class engine and pipeline set, and retires the old PythonWhisperKittranscription module that wrapped a different code path.Engine
ArgmaxOpenSourceEngine(argmax_oss_engine.py): resolves the CLI via optionalcli_path, or clone +swift build -c release --product argmax-cliunderARGMAX_OSS_CACHE_DIR(default~/.cache/openbench/argmax-oss), with optionalcommit_hashpin.transcribeanddiarizehelpers that shell out toargmax-cliwith caller-supplied flag lists.Pipelines
ArgmaxOpenSourceTranscriptionPipeline— runstranscribe, parses JSON report segments/words (including per-word timings when present).ArgmaxOpenSourceDiarizationPipeline— runsdiarize, produces RTTM compatible with existing annotation loading.ArgmaxOpenSourceOrchestrationPipeline— diarize then transcribe and merge speaker labels using word timing.Aliases and removals
whisperkit.pytranscription pipeline is removed.whisperkit-*transcription aliases (e.g. tiny, large-v3, large-v3-turbo) now target the OSS transcription pipeline and configs (same alias names for benchmark continuity).argmax-oss-diarization,argmax-oss-orchestration-tiny(plus orchestration config pattern consistent with other orchestration entries).Testing
openbench-cli evaluate(or pipeline smoke) with awhisperkit-*orargmax-oss-*alias after ensuringargmax-cliis built orcli_pathis set.