Modelpublic

gcoli/whisper-large-v3-swiss-german-gguf-q8_0

sourceHugging Faceotherupdated 2mo agoView on Hugging Face

0likes25downloads

Model Card

Whisper Large-v3 Swiss German – GGUF Q8_0

Q8_0-quantized GGUF conversion of openai/whisper-large-v3 with the LoRA adapter Flurin17/whisper-large-v3-peft-swiss-german merged into the weights. This is a standalone checkpoint for `handy-computer/transcribe.cpp`.

Usage

bash

ffmpeg -i input.m4a -ar 16000 -ac 1 input.wav

build/bin/transcribe-cli \
  -m whisper-large-v3-swiss-german-Q8_0.gguf \
  --language de \
  input.wav

For Swiss German transcription, de is the recommended Whisper language token and transcribe is the intended task.

Format and compatibility

—Format: GGUF Q8_0
—Runtime: handy-computer/transcribe.cpp
—Source quantization: the validated F16 GGUF variant
—Not compatible with oMLX, which expects MLX Safetensors

Use `gcoli/whisper-large-v3-swiss-german-mlx-fp16` for oMLX.

Provenance

—Base revision: 1ecca609f9a5ae2cd97a576a9725bc714c022a93
—Adapter revision: 2ae117cf342bc57d6068066181a9d359e98a2961
—transcribe.cpp converter and quantizer revision: 856d7c10a1a864b900e066b7c9801edf373f5148
—Quantization preset: Q8_0

The adapter was merged into the base model in FP16. The resulting F16 GGUF was then quantized using transcribe-quantize. Tokenizer, frontend and model metadata remain embedded in the GGUF. quantization_provenance.json records the exact F16 source checksum.

Evaluation and limitations

The build performs checksum validation and a real runtime transcription test. Independent Swiss German WER and controlled performance comparisons between F16 and Q8_0 have not yet been published. Quantization can introduce small accuracy differences.

Whisper can hallucinate or omit text, particularly with noise, silence, overlapping speakers, uncommon dialects, or specialized vocabulary. Do not use its output as the sole basis for high-impact decisions.

License and usage conditions

SwissDial CC BY-NC 4.0 with no-reidentification condition

The Swiss German adaptation was trained on the SwissDial dataset. Use is limited to non-commercial purposes under CC BY-NC 4.0, attempts to re-identify SwissDial speakers are prohibited, and SwissDial must be attributed and cited in research use.

The Whisper base model remains subject to Apache-2.0. This repository grants no additional rights to upstream models, training data, or software.