CoolFace
Modelpublic

shaobai880824/breeze-asr-25-local-hokkien_v1

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes29downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

breeze-asr-25-local-hokkian_v1

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: 0.6065
  • —Semantic Similarity: 0.8492

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
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 16
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 5000

Training results

Training LossEpochStepValidation LossSemantic Similarity
1.33450.12825001.29930.7334
1.13850.256410001.11140.7649
1.0240.384615001.01160.7790
0.9220.512820000.90150.8011
0.82320.641025000.82400.8102
0.76680.769130000.75360.8223
0.6910.897335000.69400.8340
0.56241.025440000.64800.8410
0.41321.153645000.61990.8470
0.40851.281850000.60650.8492

Framework versions

  • —Transformers 4.53.3
  • —Pytorch 2.7.1+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.21.2