This repository contains the conversion of
openai/whisper-large-v3 to the
CTranslate2 model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as
faster-whisper.
1from faster_whisper import WhisperModel
2
3model = WhisperModel("large-v3")
4
5segments, info = model.transcribe("audio.mp3")
6for segment in segments:
7 print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
ct2-transformers-converter --model openai/whisper-large-v3 --output_dir faster-whisper-large-v3 \
--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.
