An unofficial MLX conversion of KBLab/kb-whisper-large by KBLab (the National Library of Sweden's data lab), for running
locally on Apple Silicon with mlx-whisper. Published by the
Tibber-se organisation as a convenience for colleagues and the community. It is not affiliated with or
endorsed by KBLab, and comes with no support. All credit for the model goes to them.
uvx --from mlx-whisper mlx_whisper recording.m4a --model Tibber-se/kb-whisper-large-mlx --language sv -f srt
Needs an Apple Silicon Mac and ffmpeg. The weights stay on your machine and so does the audio.
KBLab/kb-whisper-large at revision d5d5984b4d8f7c4847a8ea203f1976285fb28300 (Apache-2.0).--dtype float16.weights.safetensors (named for the mlx_whisper loader on PyPI) and config.json.
Same tensors as the converter's own model.safetensors output.Word error rate on 100 clips of the FLEURS test split (Swedish, CC-BY-4.0), one run, on an Apple Silicon Mac:
| WER | |
|---|---|
whisper-large-v3-turbo (MLX) |
8.7% |
KBLab/kb-whisper-large through transformers (fp32, original weights) |
4.9% |
| This model | 5.1% (median clip 2.7%, worst clip 33%) |
Corpus WER is within about 0.3 points of the original weights. FLEURS is clean read speech, so real meetings and calls will score worse. Normalisation lowercases and strips punctuation but does not normalise numbers. A single run on 100 clips per language is a sanity check, not a benchmark.
KBLab/kb-whisper-large