breeze-asr-25-final-chinese

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: 1.2503
• Wer: 95.6195

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
1.5631	0.2563	100	1.4911	97.4343
1.3571	0.5127	200	1.3993	96.6208
1.3228	0.7690	300	1.3090	96.3705
1.0798	1.0231	400	1.2559	95.9950
0.8171	1.2794	500	1.2503	95.6195

Framework versions

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