benchmarkcentral/whisper-small-fa

Whisper Small fa - Mahdi Aspanani

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3673
• Wer: 37.0099

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2929	0.4055	1000	0.4922	48.5195
0.2242	0.8110	2000	0.4087	41.2283
0.1258	1.2165	3000	0.3834	38.2551
0.1075	1.6221	4000	0.3673	37.0099

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Tokenizers 0.19.1