whisper-large-v3-sr

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3961
• Wer: 17.2694

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0498	4.81	1000	0.2004	20.1799
0.0042	9.62	2000	0.3225	18.2395
0.0001	14.42	3000	0.3799	17.2694
0.0001	19.23	4000	0.3961	17.2694

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1