whisper-large-v3-swiss-german-coreml

Whisper Large-v3 Swiss German – WhisperKit/CoreML

Provenance: this checkpoint is openai/whisper-large-v3 with the LoRA adapter Flurin17/whisper-large-v3-peft-swiss-german merged into the weights (see merge_provenance.json). The licence terms of that adapter and its training data apply.

WhisperKit-compatible CoreML conversion of openai/whisper-large-v3 with the LoRA adapter Flurin17/whisper-large-v3-peft-swiss-german merged into the model weights before conversion.

Intended use

On-device transcription of Swiss German speech into German text on Apple Silicon through WhisperKit. Use de as the language and transcribe as the task. Accuracy and runtime characteristics of this CoreML conversion have not yet been independently benchmarked.

Bundle size: approximately 2.9 GB (uncompressed float16 conversion).

Sources

• Base model: https://huggingface.co/openai/whisper-large-v3
• PEFT adapter: https://huggingface.co/Flurin17/whisper-large-v3-peft-swiss-german
• Converter/runtime: https://github.com/argmaxinc/whisperkittools

Conversion

1. Load openai/whisper-large-v3 in float16.
2. Load the PEFT LoRA adapter and merge it with merge_and_unload.
3. Save the standalone Transformers checkpoint.
4. Convert that checkpoint using whisperkit-generate-model.

Pinned revisions:

• Base: 1ecca609f9a5ae2cd97a576a9725bc714c022a93
• Adapter: 2ae117cf342bc57d6068066181a9d359e98a2961
• whisperkittools: 84f77a83c8f530022ae55fbb1a64b3351ef63c7a

Conversion verification

The default whisperkittools PyTorch-to-CoreML correctness tests completed successfully on Apple Silicon:

Decoder token argmax accuracy was 100% in the converter test. These values measure conversion fidelity and static operator support; they are not an ASR accuracy or real-device speed benchmark.

Application testing

The model was tested successfully in Blitztegschter, a fork of the Blitztext app.

Qualitative observations on Apple Silicon M5:

• better recognition accuracy than the tested Whisper Large-v3 Turbo variant;
• faster transcription than the tested Turbo variant;
• subjectively comfortable waiting time during normal application use.

A similar Large-v3 versus Turbo result had previously been observed on an Apple Silicon M1 Max even without Swiss German fine-tuning. Testing this fine-tuned CoreML bundle on the M1 Max is still pending.

These are practical, qualitative observations rather than a controlled benchmark. Results can vary with hardware, audio quality, dialect, recording length, decoding settings, and application integration.

Limitations

Whisper can hallucinate or omit text, especially with noise, silence, rare dialects, overlapping speakers, or domain-specific vocabulary. Do not use the output as the sole basis for high-impact decisions. Obtain consent before transcribing people.

License

This model is provided under the SwissDial CC BY-NC 4.0 with no-reidentification condition. The applicable license information and access to the license terms are available here:

https://form.jotform.com/223344961502048

The repository is not gated. Downloading the files does not remove or replace the user's obligation to comply with the applicable license terms.

This repository does not grant additional rights to other upstream models, software, or dependencies. Each user is responsible for reviewing and complying with their applicable licenses, usage conditions, attribution requirements, and distribution restrictions.

In particular, users must independently verify the applicable terms for:

• openai/whisper-large-v3;
• Flurin17/whisper-large-v3-peft-swiss-german;
• WhisperKit, whisperkittools, Core ML, and their dependencies.

Availability of files on Hugging Face should not be interpreted as permission for uses outside the linked license terms.