AsrTaskModel

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4220
• Wer: 0.2541

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0261	0.5556	500	3.1243	0.9989
1.1139	1.1111	1000	0.9005	0.5382
0.8059	1.6667	1500	0.6447	0.3916
0.5712	2.2222	2000	0.5581	0.3395
0.5164	2.7778	2500	0.4805	0.2998
0.3958	3.3333	3000	0.4717	0.2820
0.4108	3.8889	3500	0.4494	0.2692
0.3403	4.4444	4000	0.4507	0.2588
0.3087	5.0	4500	0.4220	0.2541

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1