my zh CN asr cv13 model This model is a fine tuned version of jonatasgrosman/wav2vec2 large xlsr 53 chinese zh cn on the common voice 13 0 dataset. It achieves the following results on the evaluation set: Loss: 0.1614 Cer: 0.0674 Wer: 0.375 Model description More information needed Intended uses & limitations More information needed Training and evaluation data More information needed Training procedure Training hyperparameters The following hyperparameters were used during training: learning rate: 1e 05 train batch size: 8 eval batch size: 8 seed: 42 gradient accumulation steps: 2 total train batch size: 16 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e 08 lr scheduler type: linear lr scheduler warmup steps: 500 training steps: 2000 mixed precision training: Native AMP Training results Training Loss Epoch Step Validation Loss Cer Wer : : : : : : : : : : : : 0.0489 249.002 1000 0.1566 0.0638 0.375 0.0224 499.002 2000 0.1614 0.0674 0.375 Framework versions Transformers 4.40.1 Pytorch 2.2.1+cu121 Datasets 2.19.0 Tokenizers 0.19.1
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy