zagibest/whisper-small-custom-data-google

Whisper Small MN with custom data + Common voice + Google Fluers - Zagi

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

• Loss: 0.5343
• Wer: 34.5621

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: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1792	2.59	500	0.4204	38.2103
0.0121	5.18	1000	0.4673	36.5634
0.0034	7.77	1500	0.4964	35.6309
0.0009	10.36	2000	0.5044	34.7366
0.0007	12.95	2500	0.5166	34.7366
0.0004	15.54	3000	0.5271	34.5785
0.0003	18.13	3500	0.5323	34.5948
0.0003	20.73	4000	0.5343	34.5621

Framework versions

• Transformers 4.39.1
• Pytorch 2.0.1+cu117
• Datasets 2.18.0
• Tokenizers 0.15.2