metadata

library_name: transformers
tags:
  - asr
  - whisper
  - russian
datasets:
  - mozilla-foundation/common_voice_11_0
language:
  - ru
metrics:
  - wer

Model Details

This is a version of openai/whisper-large-v3 finetuned for better support of Russian language.

Dataset used for finetuning is Common Voice 11.0, Russian part.

After preprocessing of the original dataset (train + test + validation splits were mixed and split to new train + test by 0.95/0.05) the original Whisper v3 has WER 9.2 while the finetuned version shows 6.31

Work in progress

This model is in WIP state for now. The goal is to finetune it for speech recognition of phone calls as much as possible. If you want to contribute and you know or have any good dataset please let me know. Your help will be much appreciated.