indic-whisper-ml-reverse-high-lr

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0941

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: 0.0002
• train_batch_size: 128
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 837
• training_steps: 8365

Training results

Training Loss	Epoch	Step	Validation Loss
0.0843	0.9779	1637	0.0804
0.0643	1.9558	3274	0.0678
0.0426	2.9337	4911	0.0675
0.0253	3.9116	6548	0.0832
0.0172	4.8895	8185	0.0941

Framework versions

• Transformers 4.51.1
• Pytorch 2.8.0+cu128
• Datasets 4.4.1
• Tokenizers 0.21.4