mn720/inctraining

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: 0.4483
• Wer: 42.9584

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
0.8089	0.0682	500	0.8624	73.2282
0.6106	0.1364	1000	0.6437	59.8234
0.539	0.2045	1500	0.5589	51.8256
0.462	0.2727	2000	0.5167	48.5304
0.4342	0.3409	2500	0.4888	46.1205
0.4226	0.4091	3000	0.4673	44.8168
0.3951	0.4772	3500	0.4545	43.7128
0.4014	0.5454	4000	0.4483	42.9584

Framework versions

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