deepdml/whisper-small-gl-cv17-timestamps-v0

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: 0.3490
• Wer: 15.6898

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
0.1839	1.8182	1000	0.2678	14.0494
0.0733	3.6364	2000	0.2725	13.9146
0.0356	5.4545	3000	0.3014	15.0055
0.0194	7.2727	4000	0.3319	14.6196
0.0141	9.0909	5000	0.3490	15.6898

Framework versions

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