Whisper-Anuj-small-Telugu-final

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: 0.1426
• Wer: 34.9876
• Cer: 11.4531

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: 6
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 24
• 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
0.0642	3.9474	600	0.1178	43.0273	8.8399
0.0046	7.8947	1200	0.1248	35.9801	8.3327
0.0003	11.8421	1800	0.1426	34.9876	11.4531

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1