Whisper distil-large-v3-ru model for CTranslate2

This repository contains the conversion of bond005/whisper-large-v3-ru-podlodka 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("avazir/whisper-ct2-podlodka-int8")

segments, info = model.transcribe("audio.mp3", language="ru", condition_on_previous_text=False)
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 bond005/whisper-large-v3-ru-podlodka \
  --output_dir whisper-ct2-podlodka-int8 \
  --copy_files tokenizer.json \
  --quantization int8 \
  --force

Note that the model weights are saved in INT8. 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.