wriothsly/whisper-small-as

Whisper Small as - Debojitdutta

This model is a fine-tuned version of openai/whisper-small on the main1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Wer: 0.6648

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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
0.0055	6.6225	1000	0.0060	2.8886
0.0009	13.2450	2000	0.0037	1.5589
0.0003	19.8675	3000	0.0002	0.6878
0.0	26.4901	4000	0.0000	0.6648
0.0	33.1126	5000	0.0000	0.6648

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1