wandererupak/whisper-small-n-demo-ultimate-train-Y

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:

• Loss: 0.4382
• Wer: 54.2126
• Cer: 20.4236

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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.0737	0.9965	285	0.5120	65.7480	22.8946
0.7473	1.9930	570	0.4511	59.9606	22.3471
0.4665	2.9895	855	0.4293	54.2913	20.4884
0.3401	3.9860	1140	0.4382	54.2126	20.4236

Framework versions

• Transformers 5.2.0
• Pytorch 2.9.0+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2