whisper-small_new

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: 0.1668
• Wer: 15.3492

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: 64
• eval_batch_size: 64
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.3889	0.0	1	3.1044	49.3314
0.1707	0.29	1000	0.2347	20.9505
0.15	0.58	2000	0.1952	17.9738
0.1331	0.88	3000	0.1765	16.4836
0.1016	1.17	4000	0.1703	15.6290
0.0966	1.46	5000	0.1668	15.3492

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0
• Datasets 2.11.0
• Tokenizers 0.13.3