whisper-lt-finetune

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3634
• Wer: 28.1159

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: 5e-05
• 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: 250
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.399	0.9	500	0.4877	49.1790
0.1925	1.8	1000	0.4019	39.1325
0.0734	2.7	1500	0.3989	37.5581
0.0324	3.6	2000	0.3947	32.9662
0.0053	5.4	3000	0.3708	29.2808
0.0007	7.19	4000	0.3634	28.1159

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2