arsaeb/whisper-small-challenge

openai/whisper-small

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

• Loss: 1.2348
• Wer: 32.9977

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0137	5.005	500	1.1570	33.4424
0.0018	10.01	1000	1.2348	32.9977

Framework versions

• Transformers 4.48.3
• Pytorch 2.4.0+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0