wav2vec2 xls r 300m hebrew This model is a fine tuned version of facebook/wav2vec2 xls r 300m on the private datasets in 2 stages firstly was fine tuned on a small dataset with good samples Then the obtained model was fine tuned on a large dataset with the small good dataset, with various samples from different sources, and with an unlabeled dataset that was weakly labeled using a previously trained model. Small dataset: split size(gb) n samples duration(hrs) train 4.19 20306 28 dev 1.05 5076 7 Large dataset: split size(gb) n samples duration(hrs) train 12.3 90777 69 dev 2.39 20246 14 ( weakly labeled data wasn't used in validation set) After firts training it achieves: on small dataset Loss: 0.5438 WER: 0.1773 on large dataset WER: 0.3811 after second training: on small dataset WER: 0.1697 on large dataset Loss: 0.4502 WER: 0.2318 Model description More information needed Intended uses & limitations More information needed Training and evaluation data More information needed Training procedure Training hyperparameters First training The following hyperparameters were used during training: learning rate: 0.0003 train batch size: 8 eval batch size: 8 seed: 42 distributed type: multi…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy