TheTobyB/whisper-large-v3-turbo-german-ct2

Whisper large-v3 model for CTranslate2

This repository contains the conversion of primeline/whisper-large-v3-turbo-german to the CTranslate2 model format.

This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.

It has specifically been optimized to be used with Speaches.ai using this model conversation as a reference: Systran/faster-whisper-large-v3

Conversion details

The original model was converted with the following command:

ct2-transformers-converter --model primeline/whisper-large-v3-turbo-german --output_dir whisper-large-v3-turbo-german-ct2 \
    --copy_files preprocessor_config.json --quantization float16

Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the `compute_type` option in CTranslate2.

More information

For more information about the original model, see its [model card](https://huggingface.co/openai/whisper-large-v3) and the derived model optimized for German language, see its [model card](primeline/whisper-large-v3-turbo-german).