Downloads · 30 days
89
52% of all-time downloads
sebastian-duadigital/whisperkit-kb-whisper-small
whisperkit-kb-whisper-small is a automatic speech recognition model from sebastian-duadigital. Use it when you need speech turned into text. It is set up for whisperkit. The card lists the license as apache-2.0.
A CoreML conversion of KBLab/kb-whisper-small, the Swedish-tuned Whisper small model from the National Library of Sweden, packaged in the folder layout that WhisperKit expects. It exists so that Dikta, an offline dict…
Downloads · 30 days
89
52% of all-time downloads
All-time downloads
170
Public
Repo size
484 MB
Likes
0
Public
Click a slice to open those files.
.bin484 MB · 99%
From the Hugging Face model README
A CoreML conversion of KBLab/kb-whisper-small, the Swedish-tuned Whisper small model from the National Library of Sweden, packaged in the folder layout that WhisperKit expects. It exists so that Dikta, an offline dictation app for macOS, can download a Swedish model it controls.
KBLab_kb-whisper-small/
AudioEncoder.mlmodelc/
MelSpectrogram.mlmodelc/
TextDecoder.mlmodelc/
config.json
generation_config.json
About 464 MB in total. config.json and generation_config.json are copied verbatim from the source checkpoint. No tokenizer files are included; WhisperKit resolves the Whisper tokenizer from its default repository.
| Item | Value |
|---|---|
| Source checkpoint | KBLab/kb-whisper-small, revision 3564d61a42fc210ceaa55a22a96dd64478959c78 (Stage 2 default) |
| Converter | Argmax whisperkittools, commit 84f77a83c8f530022ae55fbb1a64b3351ef63c7a |
| Conversion host | Apple M2 Max, macOS 26.6, Xcode 27.0, Python 3.11, torch 2.5.0, coremltools 9.0 |
| Reproduction | dikta-macos/bench/convert/convert.sh in the Dikta repository, which downloads the pinned revision and runs the converter end to end |
Weights are unchanged from the source; only the file format differs.
Word error rate on a fixed, seeded 20-clip sample per language from the FLEURS test split, scored with jiwer after lowercasing and punctuation stripping. Same harness for every row.
| Model | Swedish | English |
|---|---|---|
| This model | 3.5% | 54.2% |
openai_whisper-large-v3-v20240930_turbo_632MB | 10.1% | 6.7% |
openai_whisper-small | 18.5% | 9.9% |
Use it for Swedish only. It is not a general multilingual model; English output is poor.
let pipe = try await WhisperKit(
model: "KBLab_kb-whisper-small",
modelRepo: "sebastian-duadigital/whisperkit-kb-whisper-small"
)
let result = try await pipe.transcribe(audioPath: "clip.wav", decodeOptions: .init(language: "sv"))
The weights are released by KBLab under Apache 2.0, and this conversion keeps that license. If you use the model in research, cite KBLab's paper:
Vesterbacka, L., Rekathati, F., Kurtz, R., Sikora, J., Toftgård, A. (2025)
Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition.
Proc. Interspeech 2025, 758-762, doi: 10.21437/Interspeech.2025-2646