whisper-base-gcf

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

• Loss: 2.4385
• Wer: 100.1274

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: 16
• eval_batch_size: 8
• seed: 42
• 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: 100
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9963	1.4085	200	3.4896	101.2739
0.6015	2.8169	400	3.0877	1097.9618
0.3216	4.2254	600	2.8618	99.7452
0.2368	5.6338	800	2.6891	100.1274
0.1739	7.0423	1000	2.5483	421.6561
0.1892	8.4507	1200	2.4829	104.5860
0.1273	9.8592	1400	2.4358	1683.6943
0.1256	10.5634	1500	2.4385	100.1274

Framework versions

• Transformers 5.5.0
• Pytorch 2.4.1+cu124
• Datasets 3.6.0
• Tokenizers 0.22.2