Skarrea/faster-nb-whisper-large

NbAiLab nb-whisper-large model for CTranslate2

This repository contains the conversion of NbAiLab/nb-whisper-large to the CTranslate2 model format.

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

Conversion details

The original model was converted with the following command:

ct2-transformers-converter --model NbAiLab/whisper-large --output_dir faster-nb-whisper-large \
    --copy_files tokenizer.json 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.