alexachang/whisper-hokkien-mandarin

<!-- 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. -->

whisper-hokkien-mandarin

This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.5804
• —eval_cer: 30.6452
• —eval_runtime: 346.9786
• —evalsamplesper_second: 4.796
• —evalstepsper_second: 0.599
• —epoch: 2.5304
• —step: 5000

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: 0.0001
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use 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
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.52.4
• —Pytorch 2.1.0+cu118
• —Datasets 3.6.0
• —Tokenizers 0.21.2