Skip to content
ModelListedExternal
Browse files

Whisperkit Coreml

WhisperKit-compatible Core ML models used by Vurbo.ai. Converted with argmaxinc/whisperkittools.

Sourcehuggingface.co/IPEVO/whisperkit-coreml/tree/de3f69583f8a7fb6d4a9897d7f66d9d8319c6ded
KindOtherBase modelMediaTek-Research/Breeze-ASR-26VersionRevision de3f695Bgrade

Model source

Kind
Other
File size
243 B–929 MB
Base model
MediaTek-Research/Breeze-ASR-26
Version
vRevision de3f695
Updated
Oct 26, 2026
Downloads
15
Source
Hugging Face

Source description

IPEVO WhisperKit CoreML Models

WhisperKit-compatible Core ML models used by Vurbo.ai. Converted with argmaxinc/whisperkittools.

Models

FolderBase modelPrecisionSizeNotes
breeze-asr-26-q8MediaTek-Research/Breeze-ASR-268-bit palettized~1.5GBTaiwanese Hokkien (台語) ASR, outputs Traditional Chinese

Attribution

breeze-asr-26-q8 is a derivative of Breeze-ASR-26 by MediaTek Research (Apache License 2.0), quantized to 8-bit and converted to Core ML for on-device inference via WhisperKit. config.json / tokenizer.json are from openai/whisper-large-v2 (same vocabulary).

Sources

1 source
Hugging FacePrimaryVersion de3f69583f8a7fb6d4a9897d7f66d9d8319c6ded
huggingface.co/IPEVO/whisperkit-coreml/tree/de3f69583f8a7fb6d4a9897d7f66d9d8319c6ded

Verified Oct 26

Download files

Model artifacts

9 artifacts

breeze-asr-26-q8/AudioEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 985e26115823…16e1 · Hugging Face

Download file

breeze-asr-26-q8/AudioEncoder.mlmodelc/coremldata.bin

bin · 408 B · SHA-256 4bb70e01c6fb…b9bc · Hugging Face

Download file

breeze-asr-26-q8/AudioEncoder.mlmodelc/weights/weight.bin

bin · 610 MB · SHA-256 c588e3437b81…1839 · Hugging Face

Download file

breeze-asr-26-q8/MelSpectrogram.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 28e8c877c201…058d · Hugging Face

Download file

breeze-asr-26-q8/MelSpectrogram.mlmodelc/coremldata.bin

bin · 389 B · SHA-256 612a62b9b28e…9f3a · Hugging Face

Download file

breeze-asr-26-q8/MelSpectrogram.mlmodelc/weights/weight.bin

bin · 346 KB · SHA-256 801024dbc7a8…1c83 · Hugging Face

Download file

breeze-asr-26-q8/TextDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 64ff70016fe1…befc · Hugging Face

Download file

breeze-asr-26-q8/TextDecoder.mlmodelc/coremldata.bin

bin · 698 B · SHA-256 e8245cf53b87…0daa · Hugging Face

Download file

breeze-asr-26-q8/TextDecoder.mlmodelc/weights/weight.bin

bin · 929 MB · SHA-256 4967ffd68965…5d68 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 7huggingface.co/IPEVO/whisperkit-coreml

--- license: apache-2.0 base_model: MediaTek-Research/Breeze-ASR-26 tags: - whisperkit - coreml - automatic-speech-recognition - taiwanese-hokkien --- # IPEVO WhisperKit CoreML Models WhisperKit-compatible Core ML models used by [Vurbo.ai](https://vurbo.ai). Converted with [argmaxinc/whisperkittools](https://github.com/argmaxinc/whisperkittools). ## Models | Folder | Base model | Precision | Size | Notes | |--------|-----------|-----------|------|-------| | `breeze-asr-26-q8` | [MediaTek-Research/Breeze-ASR-26](https://huggingface.co/MediaTek-Research/Breeze-ASR-26) | 8-bit palettized | ~1.5GB | Taiwanese Hokkien (台語) ASR, outputs Traditional Chinese | ## Attribution `breeze-asr-26-q8` is a derivative of Breeze-ASR-26 by MediaTek Research (Apache License 2.0), quantized to 8-bit and converted to Core ML for on-device inference via WhisperKit. `config.json` / `tokenizer.json` are from [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) (same vocabulary).

NoteOct 26huggingface.co/IPEVO/whisperkit-coreml

Source context: 15 downloads · 1 likes · Pipeline automatic-speech-recognition · Library whisperkit · Repo IPEVO/whisperkit-coreml

NoteAug 7huggingface.co/IPEVO/whisperkit-coreml

Source context: 49 downloads · 0 likes · Pipeline automatic-speech-recognition · Library whisperkit · Repo IPEVO/whisperkit-coreml