sew-timit-upsample_stage3

This model is a fine-tuned version of patrickvonplaten/sew-small-100k-timit on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0245
• Wer: 0.0059
• Cer: 0.0012

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1801	3.8071	1500	0.1359	0.2615	0.0461
0.1185	7.6142	3000	0.0910	0.1547	0.0260
0.0831	11.4213	4500	0.0543	0.0713	0.0133
0.0504	15.2284	6000	0.0345	0.0316	0.0063
0.0367	19.0355	7500	0.0245	0.0059	0.0012

Framework versions

• Transformers 4.51.3
• Pytorch 2.2.1
• Datasets 3.6.0
• Tokenizers 0.21.1