Downloads · 30 days
0
frictional123/sherpa-onnx-kb-whisper-int8
sherpa-onnx-kb-whisper-int8 is a machine learning model from frictional123. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
sherpa-onnx-compatible INT8 ONNX exports of KBLab's Swedish-tuned Whisper models. Same encoder/decoder split + tokens.txt format as csukuangfj/sherpa-onnx-whisper-.
Downloads · 30 days
0
Access
Public
Updated May 7, 2026
Repo size
3.1 GB
Likes
0
Public
Click a slice to open those files.
.onnx3.1 GB · 100%
From the Hugging Face model README
sherpa-onnx-compatible INT8 ONNX exports of KBLab's Swedish-tuned Whisper models. Same encoder/decoder split + tokens.txt format as csukuangfj/sherpa-onnx-whisper-*.
| Variant | Encoder | Decoder | Total |
|---|---|---|---|
| small | kb-whisper-small-encoder.int8.onnx (112 MB) | kb-whisper-small-decoder.int8.onnx (262 MB) | ~376 MB |
| medium | kb-whisper-medium-encoder.int8.onnx (374 MB) | kb-whisper-medium-decoder.int8.onnx (571 MB) | ~947 MB |
| large | kb-whisper-large-encoder.int8.onnx (767 MB) | kb-whisper-large-decoder.int8.onnx (1.01 GB) | ~1.78 GB |
Each variant also has a kb-whisper-{size}-tokens.txt (~800 KB, identical across variants — multilingual Whisper tokenizer).
PyTorch safetensors → OpenAI Whisper shell (state dict remapped) → sherpa-onnx encoder/decoder ONNX → INT8 dynamic quantization (MatMul ops only). Export script: see scribe/scripts/kb-whisper-export (private until cleaned up for public release).
import sherpa_onnx
recognizer = sherpa_onnx.OfflineRecognizer.from_whisper(
encoder="kb-whisper-large-encoder.int8.onnx",
decoder="kb-whisper-large-decoder.int8.onnx",
tokens="kb-whisper-large-tokens.txt",
language="sv",
task="transcribe",
provider="cpu",
)
Apache-2.0, inherited from the base KBLab/kb-whisper-* models.