St4n/whisper-small-en-0328

Whisper Small en - Stan

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

• Loss: 0.3236
• Wer: 8.6378

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: 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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5755	0.61	100	0.5716	8.6029
0.1769	1.23	200	0.2722	8.3659
0.1153	1.84	300	0.2791	8.7842
0.0356	2.45	400	0.2852	8.7981
0.0208	3.07	500	0.2923	8.6866
0.0105	3.68	600	0.3050	8.6517
0.0032	4.29	700	0.3126	8.6238
0.0033	4.91	800	0.3174	8.6308
0.0028	5.52	900	0.3227	8.5611
0.0017	6.13	1000	0.3236	8.6378

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2