wav2vec2 xls r juznevesti This model for Serbian ASR is based on the facebook/wav2vec2 xls r 300m model and was fine tuned with 58 hours of audio and transcripts from Južne vesti, programme '15 minuta'. For more info on the dataset creation see this repo. Metrics Evaluation is performed on the dev and test portions of the JuzneVesti dataset dev test : : : WER 0.295206 0.290094 CER 0.140766 0.137642 Usage in transformers Tested with transformers==4.18.0 , torch==1.11.0 , and SoundFile==0.10.3.post1 . Training hyperparameters In fine tuning, the following arguments were used: arg value per device train batch size 16 gradient accumulation steps 4 num train epochs 20 learning rate 3e 4 warmup steps 500
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy