libri-alpha-0.75-Temp-1-att-take-2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 44.5402
• Wer: 0.1081

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: 0.0002
• 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_ratio: 0.2
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
118.8957	0.45	400	46.1043	0.1056
118.7076	0.9	800	44.1911	0.1037
106.9074	1.35	1200	42.3038	0.1028
107.4129	1.79	1600	48.0483	0.1030
106.3615	2.24	2000	60.1421	0.1029
106.3024	2.69	2400	48.8849	0.1028
107.8432	3.14	2800	42.9345	0.1072
107.6928	3.59	3200	44.5402	0.1081

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1
• Datasets 2.6.1
• Tokenizers 0.13.1