dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript

<!-- 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-large-v3-chichewa-variant-b-normalized-transcript

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 1.6772
• —Wer: 56.0482
• —Cer: 25.0424

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: 7.5e-06
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 0.05
• —training_steps: 3000

Training results

Framework versions

• —Transformers 5.8.1
• —Pytorch 2.6.0+cu124
• —Datasets 3.6.0
• —Tokenizers 0.22.2