whisper-aviation-base

This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0366
• Wer: 60.6996

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: 16
• 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0003	166.67	1000	0.9538	75.1029
0.0001	333.33	2000	1.0000	101.0288
0.0001	500.0	3000	1.0239	58.2305
0.0001	666.67	4000	1.0366	60.6996

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1