whisper-tiny-atco2-asr

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

• Loss: 1.0505
• Wer: 112.9893

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
1.8611	12.5	50	1.5491	100.1779
0.5484	25.0	100	1.1962	91.5036
0.1272	37.5	150	1.0106	158.7189
0.0125	50.0	200	1.0290	124.3327
0.0074	62.5	250	1.0401	116.7705
0.005	75.0	300	1.0461	118.6833
0.0044	87.5	350	1.0493	113.0783
0.004	100.0	400	1.0505	112.9893

Framework versions

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