whisper-medium.en-atco2-asr

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

• Loss: 0.9216
• Wer: 29.5819

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
0.9851	12.5	50	1.0968	24.1103
0.1295	25.0	100	0.9019	82.4288
0.0379	37.5	150	0.8000	26.4680
0.008	50.0	200	0.8494	27.2687
0.0052	62.5	250	0.8890	34.2527
0.0032	75.0	300	0.9108	28.4253
0.0027	87.5	350	0.9191	29.2260
0.0023	100.0	400	0.9216	29.5819

Framework versions

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