Hugging Face's logo

RASMUS
/
wav2vec2-xlsr-1b-ru

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Russian
wav2vec2
audio
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_8_0
robust-speech-event
speech
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
wav2vec2-xlsr-1b-ru / eval_ru_without_lm.sh
RASMUS's picture
RASMUS
add eval ru without lm
7eb5517
raw
history blame
137 Bytes
python eval.py --model_id RASMUS/wav2vec2-xlsr-1b-ru --dataset mozilla-foundation/common_voice_8_0 --config ru --split test --log_outputs