whisper-small-nya

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

• Loss: 0.5086
• Wer: 27.5487

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: 2.5e-05
• train_batch_size: 8
• eval_batch_size: 4
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2671	0.99	500	0.5633	35.9244
0.1372	1.97	1000	0.4515	48.1630
0.0742	2.96	1500	0.4474	32.4985
0.0341	3.94	2000	0.4595	35.3574
0.0191	4.93	2500	0.4722	28.2930
0.0073	5.92	3000	0.4774	25.3633
0.0031	6.9	3500	0.4875	25.9539
0.0009	7.89	4000	0.4995	26.2611
0.0012	8.87	4500	0.5056	25.1861
0.0004	9.86	5000	0.5086	27.5487

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2