whisperFinetune

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

• Loss: 0.5745
• Wer: 28.7011

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: 0.001
• train_batch_size: 128
• 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: 500
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.8818	0.2778	10	1.9210	39.4679
0.7557	0.5556	20	0.6926	27.2926
0.5718	0.8333	30	0.5717	23.7559
0.421	1.1111	40	0.5161	21.5023
0.3088	1.3889	50	0.5103	21.0955
0.3415	1.6667	60	0.5155	21.6901
0.3434	1.9444	70	0.5176	30.0156
0.1371	2.2222	80	0.5303	20.6886
0.1349	2.5	90	0.5589	22.0344
0.1461	2.7778	100	0.5745	28.7011

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1.dev0
• Tokenizers 0.19.1