Model reference · open weights
kb-whisper-large is an open-weight audio or speech model from KBLab, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
KB-Whisper Large The National Library of Sweden releases a new suite of Whisper models trained on over 50,000 hours of Swedish speech. In evaluations across FLEURS, CommonVoice and NST, our best performing model reduces the Word Error Rate (WER) by an average of 47% compared to OpenAI's whisper-large-v3. The performance of smaller Whisper model sizes on Swedish speech has also substantially improved, with kb-whisper-small outperforming openai/whisper-large-v3 (a model six times its size). Table: Word Error Rate (WER) comparison between KBLab's Whisper models and the corresponding OpenAI versions. Usage We provide checkpoints in different formats: Hugging Face, whisper.cpp (GGML), onnx, and ctranslate2 (used in faster-whisper and WhisperX). 2025-05-13 Update! The default when loading our models through Hugging Face is Stage 2. As of May 2025 there exists two Stage 2 versions in addition to the default, namely Subtitle and Strict that specify the transcription style. By specifying revision="subtitle" in .frompretrained() the model version with a more condensed style of transcribing is accessed. By specifying revision="strict" in .frompretrained() the more verbatim-like version of the model is accessed. Below is an example of how this argument is passed in the .frompretrained() function The verbosity of the transcription styles of the three model versions ranges from the least verbose Subtitle, to Stage 2 (default) to the most verbose Strict. Hugging Face Inference example for using KB-Whisper with Hugging Face: Faster-whisper Faster-whisper provides fast and efficient inference via a reimplementation of Whisper using ctranslate2. WhisperX WhisperX provides a convenient method of getting accurate word level timestamps. The library combines (force aligns) the text output of Whisper with the accurate timestamps of Wav2vec2. We provide an example below of how to use KB-Whisper together with KBLab/wav2vec2-large-voxrex-swedish. Whisper.cpp / GGML We provide GGML checkpoints used in the apps whisper.cpp and MacWhisper. To use our model with whisper.cpp first clone the repository and build the library: To use the model you need to download one of the GGML checkpoints we
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | KBLab |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 1.6B |
| Variants | 1 |
| Runs with | transformers |
| Based on | openai/whisper-large-v3 |
| Released | 2025-02-14 |
| Popularity | 69k downloads / month |
| Likes | 66 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| kb-whisper-large | 1.6B | BF16 | ~3.7 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys kb-whisper-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kb-whisper-large below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="kb-whisper-large" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗