mn720/english

Whisper Small Luganda

This model is a fine-tuned version of openai/whisper-small on the Common Voice 15.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3827
• Wer: 40.4513

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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
0.6718	0.1129	500	0.7164	66.9178
0.4723	0.2258	1000	0.5436	54.4267
0.4208	0.3388	1500	0.4769	49.0925
0.3881	0.4517	2000	0.4404	45.3112
0.3739	0.5646	2500	0.4167	43.9251
0.3387	0.6775	3000	0.3993	41.2913
0.3405	0.7904	3500	0.3886	41.2099
0.3089	0.9033	4000	0.3827	40.4513

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.2+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1