wav2vec2 xls r 300m cs cv8 This model is a fine tuned version of facebook/wav2vec2 xls r 300m on the common voice 8.0 dataset. It achieves the following results on the evaluation set: WER: 0.49575384615384616 CER: 0.13333333333333333 Usage The model can be used directly (without a language model) as follows: Evaluation The model can be evaluated using the attached eval.py script: Training and evaluation data The Common Voice 8.0 train and validation datasets were used for training Training hyperparameters The following hyperparameters were used during training: learning rate: 7e 4 train batch size: 32 eval batch size: 8 seed: 42 gradient accumulation steps: 20 total train batch size: 640 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e 08 lr scheduler type: linear lr scheduler warmup steps: 500 num epochs: 50 mixed precision training: Native AMP Framework versions Transformers 4.16.0.dev0 Pytorch 1.10.1+cu102 Datasets 1.17.1.dev0 Tokenizers 0.11.0
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy