whisper-small-persian

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8237
• Wer: 62.5

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.89	2	5.1135	87.5
No log	1.78	4	3.1980	75.0
No log	2.67	6	2.5434	75.0
No log	4.0	9	1.8864	62.5
No log	4.44	10	1.8237	62.5

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1