whisper-small-ar-draligomaa-dataset

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

• Loss: 0.2841
• Wer Ortho: 19.2646

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho
0.3444	0.6369	100	0.3552	25.8274
0.2236	1.2739	200	0.3067	21.1163
0.2049	1.9108	300	0.2851	19.9693
0.1437	2.5478	400	0.2779	19.0788
0.0856	3.1847	500	0.2841	19.2646

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0