whisper-turbo

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0474
• Wer: 4.5742

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2594	0.4744	1000	0.2370	20.1185
0.177	0.9488	2000	0.1526	13.8271
0.1132	1.4231	3000	0.1142	10.8063
0.0963	1.8975	4000	0.0840	8.2847
0.0546	2.3719	5000	0.0632	6.2435
0.0465	2.8463	6000	0.0474	4.5742

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1