Whisper Small N - Final

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

• eval_loss: 0.6699
• eval_wer: 50.2477
• eval_cer: 17.2383
• eval_runtime: 162.322
• eval_samples_per_second: 2.169
• eval_steps_per_second: 0.271
• epoch: 13.9235
• step: 2464

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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 20
• mixed_precision_training: Native AMP

Framework versions

• Transformers 5.1.0
• Pytorch 2.9.0+cu126
• Datasets 4.5.0
• Tokenizers 0.22.2