callum-canavan/whisper-small-ga-4000

Whisper Small Ga 4000 - Callum Canavan

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 1.3939
• Wer Ortho: 65.7126
• Wer: 64.3228

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0174	7.58	500	1.1656	63.4346	60.4899
0.0009	15.15	1000	1.2670	62.3248	60.8069
0.0004	22.73	1500	1.3114	63.6974	62.2478
0.0002	30.3	2000	1.3408	64.0187	62.6225
0.0002	37.88	2500	1.3621	64.3692	63.0836
0.0001	45.45	3000	1.3791	64.3984	62.9971
0.0001	53.03	3500	1.3900	65.8294	64.4092
0.0001	60.61	4000	1.3939	65.7126	64.3228

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1