indic-whisper-reverse-ml-mft-1-0-1-15

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

• Loss: 0.0236
• Wer: 7.6923
• Cer: 1.4235

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: 64
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• 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: 2
• training_steps: 2014

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.035	2.9727	600	0.0261	11.5385	2.3132
0.0338	5.9429	1200	0.0234	7.6923	1.4235
0.035	8.9132	1800	0.0236	7.6923	1.4235

Framework versions

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