whisper-large-v3-swiss-german-mlx-q4
Q4 quantized MLX conversion of whisper-large-v3-swiss-german, derived from
openai/whisper-large-v3 plus a Swiss German PEFT adaptation trained on
SwissDial data.
This repository is intended for local speech-to-text inference with MLX-based Whisper runtimes, including oMLX through its mlx-audio STT integration.
Format
- Native MLX Whisper checkpoint
- Weight-only affine quantization
- 4-bit weights
- Group size 64
model.safetensorswith MLX tensor names- Hugging Face Whisper processor/tokenizer files included for mlx-audio/oMLX
Usage
Download the repository and point your MLX/oMLX Whisper STT engine at the local model directory or Hugging Face repo:
huggingface-cli download --local-dir whisper-large-v3-swiss-german-mlx-q4 gcoli/whisper-large-v3-swiss-german-mlx-q4
For oMLX, configure the model as a Whisper/STT model. Exact routing depends on the oMLX version and deployment config.
License and usage restrictions
SwissDial CC BY-NC 4.0 with no-reidentification condition
The Swiss German adaptation is based on SwissDial data. Use of this model is therefore restricted to non-commercial purposes under Creative Commons Attribution-NonCommercial 4.0 International, plus the SwissDial condition that users must not attempt to determine the identity of speakers in the SwissDial dataset.
Additional practical terms:
- Non-commercial use only.
- Attribute SwissDial and cite the SwissDial publication when used in research.
- Do not use this model or its outputs to identify or re-identify SwissDial speakers.
- This model is not endorsed by ETH Zurich, OpenAI, or the original adapter authors.
The Whisper base model remains under its original Apache-2.0 license. The combined adapted checkpoint is distributed under the more restrictive terms above because of the SwissDial-trained adaptation.
Provenance
This Q4 model was produced from the local FP16 MLX checkpoint by quantizing MLX Linear and Embedding weights to 4-bit affine groups. Conv, LayerNorm, positional embeddings and bias vectors remain dense.
See merge_provenance.json for the base and adapter source metadata inherited
from the FP16 conversion.
Validation
The repository contains SHA256SUMS for model.safetensors and config.json.
Structural validation checks:
- Whisper large-v3 MLX dimensions
- required processor/tokenizer files
- required representative encoder/decoder tensors
- quantization metadata in
config.json
No benchmark numbers are claimed for this Q4 variant until dialect-specific WER/CER evaluation has been run on a held-out Swiss German test set.