san2003m/whisper-small-atc0510

Whisper Small ATC - ATCText

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

• Loss: 0.2696
• Wer: 9.9247

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2728	0.84	1000	0.3054	13.2221
0.1259	1.69	2000	0.2615	10.4611
0.0558	2.53	3000	0.2588	9.9267
0.0316	3.38	4000	0.2690	9.8680
0.0136	4.22	5000	0.2696	9.9247

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2
• Datasets 2.18.0
• Tokenizers 0.15.2