whisper-medium-wolof-2-english

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

• Loss: 2.9478
• Bleu: 13.5115

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: 16
• 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: 20000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.2614	4.9200	4000	1.7721	11.6444
0.021	9.8401	8000	2.2952	12.5013
0.0057	14.7601	12000	2.6149	13.0809
0.0016	19.6802	16000	2.7852	13.0534
0.0005	24.6002	20000	2.9478	13.5115

Framework versions

• Transformers 4.41.2
• Pytorch 2.4.0+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1