Downloads · 30 days
42
1% of all-time downloads
mitchelldehaven/whisper-medium-ru
whisper-medium-ru is a automatic speech recognition model from mitchelldehaven. Use it when you need speech turned into text. It is set up for transformers.
Whisper model finetuned using audio data from Open STT Russian Dataset (https://github.com/snakers4/openstt).
Downloads · 30 days
42
1% of all-time downloads
All-time downloads
3.2K
Public
Repo size
9.2 GB
Likes
5
Public
Click a slice to open those files.
.bin3.1 GB · 100%
From the Hugging Face model README
Whisper model finetuned using audio data from Open STT Russian Dataset (https://github.com/snakers4/open_stt).
There is a differences in tokenization of source data (in our data normalization process, we replace punctucation with "" rather than Whisper's " "). This mismatch leads to a slight degradation on CommonVoice.