anatal/whisper-small-pt

Whisper Small pt - CV

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: 0.3521
• Wer: 17.1586

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
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Use OptimizerNames.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
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1452	1.4556	1000	0.2624	17.9483
0.0733	2.9112	2000	0.2660	17.1344
0.0118	4.3668	3000	0.3177	17.2583
0.0066	5.8224	4000	0.3521	17.1586

Framework versions

• Transformers 4.52.4
• Pytorch 2.8.0.dev20250515+cu128
• Datasets 3.6.0
• Tokenizers 0.21.1