Whisper-Anuj-small-Tamil

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: 0.1454
• Wer: 44.0964
• Cer: 9.0478

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: 4
• 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: 1800

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1086	3.0	600	0.1286	60.0	19.7609
0.0132	6.0	1200	0.1274	45.6225	9.3391
0.001	9.0	1800	0.1454	44.0964	9.0478

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1