deepdml/whisper-small-gl-cv17

Whisper Small gl

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2794
• Wer: 8.8310

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: 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1468	1.8182	1000	0.2098	9.3816
0.0393	3.6364	2000	0.2172	8.9370
0.0087	5.4545	3000	0.2506	8.7123
0.0034	7.2727	4000	0.2720	8.8114
0.0026	9.0909	5000	0.2794	8.8310

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1