wav2vec2-base-medical-demo

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: 0.4566
• Wer: 0.2256

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: 32
• 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.045	3.97	500	3.0058	0.9895
1.762	7.94	1000	0.5449	0.3923
0.3363	11.9	1500	0.3889	0.2890
0.173	15.87	2000	0.3992	0.2524
0.1127	19.84	2500	0.4172	0.2375
0.0805	23.81	3000	0.4576	0.2291
0.0648	27.78	3500	0.4566	0.2256

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.0.1+cpu
• Datasets 2.14.6.dev0
• Tokenizers 0.14.1