Adding Parakeet Export and Runtime - #136
Merged
Merged
Conversation
kevchengcodes
requested review from
alejandro-isaza,
carinapeng,
stikves and
tjia1818
July 31, 2026 23:10
tjia1818
approved these changes
Aug 1, 2026
stikves
reviewed
Aug 1, 2026
stikves
reviewed
Aug 1, 2026
stikves
reviewed
Aug 1, 2026
stikves
reviewed
Aug 1, 2026
stikves
reviewed
Aug 1, 2026
carinapeng
reviewed
Aug 1, 2026
carinapeng
reviewed
Aug 1, 2026
carinapeng
left a comment
carinapeng
left a comment
Contributor
There was a problem hiding this comment.
Agreed with @stikves that we might want to iterate a bit more. To me it'd be great to include in this PR the decoder advancing on blank frames needs more checking, and more testing. The other things flagged are worth considering but could be follow up PRs :)
kevchengcodes
force-pushed
the
add_parakeet_export
branch
from
August 5, 2026 23:41
7f7570d to
53cd903
Compare
tjia1818
approved these changes
Aug 6, 2026
kevchengcodes
force-pushed
the
add_parakeet_export
branch
from
August 6, 2026 17:45
9c4b3d5 to
f151066
Compare
stikves
reviewed
Aug 6, 2026
stikves
reviewed
Aug 6, 2026
stikves
approved these changes
Aug 6, 2026
stikves
left a comment
stikves
left a comment
Contributor
There was a problem hiding this comment.
Looks good overall, thank you
…-aware index for melspectogram, cache probe fix for whisper
kevchengcodes
force-pushed
the
add_parakeet_export
branch
from
August 7, 2026 17:40
36416d4 to
184a153
Compare
msnabiel
added a commit
to msnabiel/coreai-models
that referenced
this pull request
Aug 11, 2026
Resolves conflicts: - Removed ModelShapeConfig.swift (deleted upstream in apple#148) - Updated NDArray+Helpers.swift documentation for stride-aware indexing Pulls in upstream features: - Parakeet speech recognition export and runtime (apple#136) - SyncInputHandler protocol and InputContext (apple#147) - Zero-copy state binding with bind(into:) (apple#156) - Additional speech tests and config improvements - Bug fixes for forced_decoder_ids parsing, topK normalization, logits token count Preserves local iOS optimizations: - int8 KV cache quantization (2× memory reduction) - 16k default context with unreachable shape pruning - CoreAI simulator availability guards 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
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
4 participants
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
This PR adds the export and runtime for parakeet-tdt-0.6b-v3. It also does some light cleanup of the existing speech recognition Swift runtime, and renames all
speech-runner-esque terminology tospeech-recognizer. This is why you see some files deleted (they were renamed but with large changes).Closes #7
Changes
MelSpectogram.swift, such that Whisper is unaffected but Parakeet can be supportedTesting
Using this jfk.wav file as an example: