whisper-small-mlg-Oreoluwa

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

• Loss: 0.3588
• Wer: 0.1815
• Cer: 0.0681

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.7022	0.8696	500	0.3625	0.2856	0.1253
0.5500	1.7391	1000	0.3085	0.2211	0.0934
0.3486	2.6087	1500	0.3081	0.1961	0.0741
0.2930	3.4783	2000	0.3105	0.2041	0.0830
0.2068	4.3478	2500	0.3356	0.1853	0.0701
0.1288	5.2174	3000	0.3588	0.1815	0.0681

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2