kb-whisper-medium-ct2

KBLab/kb-whisper-medium model for CTranslate2

This repository contains the conversion of KBLab/kb-whisper-medium to the CTranslate2 model format.

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

Example

from faster_whisper import WhisperModel
model = WhisperModel("jestillore/kb-whisper-medium-ct2")
segments, info = model.transcribe("audio.mp3")
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Conversion details

The original model was converted with the following command:

ct2-transformers-converter --model KBLab/kb-whisper-medium --output_dir kb-whisper-medium-ct2 \
    --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.