This is a version of openai/whisper-large-v3 finetuned for better support of Russian language.
Dataset used for finetuning is Common Voice 17.0, Russian part, that contains over 200k rows.
After preprocessing of the original dataset (all splits were mixed and splited to a new train + test split by 0.95/0.05, that is 225761/11883 rows respectively) the original Whisper v3 has WER 9.84 while the finetuned version shows 6.39 (so far).
The finetuning process took over 60 hours on dual Tesla A100 80Gb.
In order to process phone calls it is highly recommended that you preprocess your records and adjust volume before performing ASR. For example, like this:
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.