wav2vec2-base-timit-coba-sandy

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6048
• Wer: 0.5118

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: 0.0001
• train_batch_size: 8
• 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: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0362	0.2008	100	3.1211	1.0
2.9869	0.4016	200	3.1039	1.0
2.9429	0.6024	300	2.9918	1.0
2.6059	0.8032	400	2.1529	1.0098
1.6444	1.0040	500	1.2032	0.9262
1.0685	1.2048	600	0.8444	0.6414
0.8178	1.4056	700	0.7169	0.5498
0.7488	1.6064	800	0.6162	0.5415
0.6292	1.8072	900	0.6048	0.5118

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 1.18.3
• Tokenizers 0.19.1