breeze-asr-25-final-corrected

This model is a fine-tuned version of MediaTek-Research/Breeze-ASR-25 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5368
• Wer: 87.7784

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_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: 100
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.0472	0.2563	100	0.9278	95.6051
0.7417	0.5127	200	0.7153	92.5346
0.6458	0.7690	300	0.6178	90.0662
0.4798	1.0231	400	0.5592	88.6815
0.3652	1.2794	500	0.5368	87.7784

Framework versions

• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2