whisper-tiny-minds14-test-finetuned

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5522
• Wer Ortho: 15.9236
• Wer: 14.9260

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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0009	15.15	500	0.4051	14.5587	13.5335
0.0003	30.3	1000	0.4404	14.8772	13.7511
0.0002	45.45	1500	0.4655	15.5596	14.4909
0.0001	60.61	2000	0.4870	15.4231	14.3168
0.0001	75.76	2500	0.5048	15.6961	14.6649
0.0	90.91	3000	0.5217	15.7871	14.7084
0.0	106.06	3500	0.5368	15.9691	14.9260
0.0	121.21	4000	0.5522	15.9236	14.9260

Framework versions

• Transformers 4.38.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2