chengyili2005/whisper-medium-spanish-english-lora

<!-- 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 Medium Spanish-English - Chengyi Li

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

• —Loss: 0.8520
• —Wer: 58.5413

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: 5e-05
• —trainbatchsize: 4
• —evalbatchsize: 4
• —seed: 42
• —gradientaccumulationsteps: 4
• —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: 20000

Training results

Framework versions

• —PEFT 0.18.1
• —Transformers 4.52.0
• —Pytorch 2.9.1+cu128
• —Datasets 4.5.0
• —Tokenizers 0.21.4