Releases: argmaxinc/WhisperKit
Releases · argmaxinc/WhisperKit
v0.3.1
What's Changed
-
macOS 13 & iOS 16 support in #40
- We have made WhisperKit available on older OS versions based on community feedback.
- Please note that macOS 13 and iOS 16 performance will be degraded in terms of prediction latency, compile time, peak memory consumption.
- We have tested and recommend using
tiny
andbase
variants on devices with these older OS versions for a stable user experience. - If you run into any output correctness issues, please switch to using
cpuAndGPU
compute units (from the default ofcpuAndNeuralEngine
) via theModelComputeOptions
init parameter. - As always, if you notice any irregularities, please post an issue here for us to follow up on.
-
Implement selecting input device by @cgfarmer4 in #51
- Thanks to @cgfarmer4, macOS users can now select their preferred microphone, not just the default one. Check out @cgfarmer4's fantastic feature walkthrough, and dive into the fully implemented sample code in the WhisperAX example app to see it in action!
New Contributors
- @eltociear made their first contribution in #43
- @cgfarmer4 made their first contribution in #51
Full Changelog: v0.3.0...v0.3.1
v0.3.0
What's Changed
- Word Timestamp support in #38
- You can now generate word level timestamps with the new decoding option
wordTimestamps: true
or via the cli with --word-timestamps - They are included on each
TranscriptionSegment
in a newwords
parameter - Following up with demo code and example app integrations in a later release
- Example json output: https://gist.github.com/ZachNagengast/f36a751bc68a3b5f2c41ada8bcc33746
- Check out this example video from @finnvoor showing it in action:
- You can now generate word level timestamps with the new decoding option
Detail_202403010956142.mp4
- Allow setting a downloadBase so downloaded models are not forced into the user's Documents folder by @jordibruin in #34
- Streaming Microphone for CLI by @jkrukowski in #35
New Contributors
- @jordibruin made their first contribution in #34
Full Changelog: v0.2.1...v0.3.0
v0.2.1
What's Changed
- Added implementation for SuppressBlankFilter by @jkrukowski in #18
- Also includes a performance improvement for the common LogitFilter operation for filling in
-infinity
probability.
- Also includes a performance improvement for the common LogitFilter operation for filling in
- Fixed issue with swift package dependencies that point to commit hashes #21 reported by @sleeper
Full Changelog: v0.2.0...v0.2.1
v0.2.0
What's Changed
- watchOS example & downloading improvements #20
You can now try out our watchOS example on any Series 9 or Ultra 2 apple watch. In order to build to it, just change the target in the WhisperAX example app:
Supported models are:
- base
- base.en
- tiny
- tiny.en
In addition to the WatchOS example app, this version includes a fix for downloading models when there is a partial download already in the filesystem. This includes the following changes:
- New init parameter
download
to allow/disallow downloading ifmodelFolder
is nil (default true)- This is particularly useful if you want to initialize a "empty" whisperkit object
modelFolder
is now an optional- Breaking change:
load
has been renamed todownload
for clarity, we will keep such changes rare moving forward
Full Changelog: v0.1.2...v0.2.0
v0.1.2
What's Changed
- Added implementation for SuppressTokensFilter by @jkrukowski in #14
- You can now use the
SuppressTokensFilter
protocol via the decoding options:
let options = DecodingOptions( supressTokens: [220, 50257] // array of tokens you want to supress ) let transcribeResult = try await whisperKit.transcribe(audioPath: path, decodeOptions: options)
- You can now use the
- Fixes and cleanup from early feedback by @ZachNagengast in #15
- New Makefile command:
make download-model MODEL=tiny
to download only the specified model instead of the entire model repo - This release also includes the new macOS 14 github runner for CI.
- New Makefile command:
New Contributors
- @jkrukowski made their first contribution in #14
Full Changelog: v0.1.1...v0.1.2
v0.1.1
What's Changed
- Fix broken Hugging Face link by @thenameless7741 in #1
- Fix memory leak by @finnvoor in #8
- Updated to semantic versioning for dependency
swift-transformers
New Contributors
- @thenameless7741 made their first contribution in #1
- @finnvoor made their first contribution in #8
Full Changelog: v0.1.0...v0.1.1
v0.1.0
Initial release 🎉