aamoshdahal/whisper-small-nepali

Whisper Small Nepali

This model is a fine-tuned version of openai/whisper-small on the Nepali Speech-to-Text Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.4741
• Wer: 41.8257

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0121	9.6154	1000	0.3463	44.6216
0.0014	19.2308	2000	0.4206	42.2300
0.0001	28.8462	3000	0.4535	41.8706
0.0	38.4615	4000	0.4684	41.8482
0.0	48.0769	5000	0.4741	41.8257

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0