devkyle/whisper-small-no-dropout

whisper-small-akan

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2208
• Wer: 9.3196

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: 0.0001
• 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: 200
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0726	10.0	250	0.8217	48.0395
0.0246	20.0	500	0.9650	44.0903
0.011	30.0	750	0.9165	40.6770
0.0022	40.0	1000	0.9419	39.9436
0.0009	50.0	1250	0.2120	9.7770
0.0002	60.0	1500	0.2179	9.0909
0.0001	70.0	1750	0.2201	9.3196
0.0001	80.0	2000	0.2208	9.3196

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1