--- tags: - generated_from_trainer metrics: - wer model-index: - name: hubert-base-libri-pruning-v2-testing5-final results: [] --- # hubert-base-libri-pruning-v2-testing5-final This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.1059 - Wer: 0.9860 ## 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: 5e-05 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1000 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | 9.0283 | 1.12 | 500 | 9.7978 | 1.0000 | | 6.3972 | 2.24 | 1000 | 5.9898 | 0.9997 | | 4.3003 | 3.36 | 1500 | 4.2828 | 0.9978 | | 3.5832 | 4.48 | 2000 | 3.6687 | 0.9973 | | 3.2064 | 5.61 | 2500 | 3.2093 | 0.9968 | | 2.8452 | 6.73 | 3000 | 2.7168 | 0.9949 | | 2.5056 | 7.85 | 3500 | 2.3288 | 0.9913 | | 2.2665 | 8.97 | 4000 | 2.1059 | 0.9860 | ### Framework versions - Transformers 4.30.0.dev0 - Pytorch 2.0.1 - Datasets 2.12.1.dev0 - Tokenizers 0.13.3