whisper-small-ur

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: 0.0029
• Wer: 76.1310

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: 100
• training_steps: 700

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.1678	2.27	100	1.0347	110.8789
0.3171	4.55	200	0.2896	54.6101
0.1408	6.82	300	0.0993	98.5782
0.0447	9.09	400	0.0261	38.4102
0.0101	11.36	500	0.0083	74.2783
0.004	13.64	600	0.0035	72.9642
0.0031	15.91	700	0.0029	76.1310

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.1
• Tokenizers 0.13.3