whisper-large-v2-jp model for CTranslate2

This repository contains the conversion of vumichien/whisper-large-v2-jp 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("arc-r/faster-whisper-large-v2-jp")

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 vumichien/whisper-large-v2-jp --output_dir faster-whisper-large-v2-jp \
    --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.