whisper-small-ham - Charles Brain

This model is a fine-tuned version of openai/whisper-small on the hamradio_voice_1_0 dataset. This is highly experimental and does not have much training data yet. That will be the next 'challenge'.

It achieves the following results on the evaluation set:

• Loss: 0.0000
• Wer: 0.0

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: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	1000.0	1000	0.0000	0.0
0.0	2000.0	2000	0.0000	0.0
0.0	3000.0	3000	0.0000	0.0
0.0	4000.0	4000	0.0000	0.0
0.0	5000.0	5000	0.0000	0.0

Framework versions

• Transformers 4.57.6
• Pytorch 2.9.1+cu130
• Datasets 4.5.0
• Tokenizers 0.22.2