whisper_small_finetuning

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: 0.2716
• Wer: 48.9738

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: 8000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2444	0.5089	1000	0.2649	48.0031
0.118	1.0178	2000	0.2419	37.8841
0.1114	1.5267	3000	0.2416	41.9230
0.0539	2.0356	4000	0.2410	30.5662
0.0464	2.5445	5000	0.2444	45.3100
0.0273	3.0534	6000	0.2561	41.4272
0.0223	3.5623	7000	0.2678	44.1767
0.0086	4.0712	8000	0.2716	48.9738

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1
• Datasets 2.19.1
• Tokenizers 0.19.1