repo_name

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6818
• Cer: 280.0

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: 16
• eval_batch_size: 16
• seed: 42
• 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
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.8222	10.0	10	5.8595	31.1111
2.5355	20.0	20	5.3513	31.1111
2.0991	30.0	30	4.7545	31.1111
1.637	40.0	40	4.1406	51.1111
1.2404	50.0	50	3.6781	44.4444
0.9007	60.0	60	3.1975	37.7778
0.6367	70.0	70	2.6794	28.8889
0.4312	80.0	80	2.2586	33.3333
0.2662	90.0	90	1.7207	280.0
0.1945	100.0	100	1.6818	280.0

Framework versions

• Transformers 4.56.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4