jethrowang/whisper-tiny_tat-esc_exp_nr_0.5_cc_0.5_embeds

<!-- 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 Tiny Taiwanese (expnr0.5cc0.5_embeds)

This model is a fine-tuned version of openai/whisper-tiny on the TAT ASR Aligned dataset. It achieves the following results on the evaluation set:

• —Loss: 2.2774
• —Cer: 41.7092

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: 0.0005
• —trainbatchsize: 64
• —evalbatchsize: 32
• —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: 681
• —training_steps: 6810
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.49.0
• —Pytorch 2.0.0.post304
• —Datasets 3.3.2
• —Tokenizers 0.21.0