whisper-small.en-atco2-asr

This model is a fine-tuned version of openai/whisper-small.en on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9789
• Wer: 44.6619

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2761	12.5	50	1.2240	36.1655
0.2584	25.0	100	0.9577	37.5890
0.0796	37.5	150	0.9088	45.7295
0.0172	50.0	200	0.9225	44.2171
0.0095	62.5	250	0.9491	35.5872
0.0067	75.0	300	0.9658	45.1512
0.0061	87.5	350	0.9757	45.1068
0.0055	100.0	400	0.9789	44.6619

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.0