Fine-tuned using this notebook

Glaswegian_Whisper

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

• Loss: 1.4788
• Wer: 40.5394

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
0.0084	16.3934	1000	1.2802	38.5588
0.0019	32.7869	2000	1.4141	39.0223
0.0002	49.1803	3000	1.4553	40.3287
0.0001	65.5738	4000	1.4788	40.5394

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1