YeBhoneLin10/openai-whisper-burmese

Whisper Small My - Ye Bhone Lin

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

• Loss: 0.2066
• Wer: 78.2715

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: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0386	7.8740	1000	0.1604	94.4679
0.0006	15.7480	2000	0.2066	78.2715

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0