output_model_shunyalabs_data_base_model_proper_feature_extractor

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: 0.5820
• Wer: 24.2800

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: 2
• eval_batch_size: 4
• 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: 500
• training_steps: 20000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5757	1.9531	2500	0.8046	47.6148
0.2328	3.9062	5000	0.6716	41.8697
0.0709	5.8594	7500	0.6649	36.1985
0.0390	7.8125	10000	0.6370	32.9789
0.0096	9.7656	12500	0.6417	30.9408
0.0052	11.7188	15000	0.6051	27.2190
0.0002	13.6719	17500	0.5878	24.6197
0.0001	15.625	20000	0.5820	24.2800

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2