whisper-large-v3-turbo-OpenSLR-GL-EN

This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3068
• Wer: 12.8695
• Bleu: 82.3838

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: 5e-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 32
• total_eval_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	Bleu
0.7917	1.0	50	0.7661	29.7044	59.6879
0.3607	2.0	100	0.4962	17.7001	75.5670
0.2587	3.0	150	0.3790	14.0952	79.7076
0.1332	4.0	200	0.3236	13.1939	81.7332
0.0952	5.0	250	0.3068	12.8695	82.3838

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0