CasperMuz/whisper-base-sna-ven-pilot

<!-- 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 Base Shona + Tshivenda Pilot

This model is a fine-tuned version of openai/whisper-base on the Cleaned WAXAL Shona and the Swivuriso Tshivenda datasets. It achieves the following results on the evaluation set:

• —eval_loss: 0.6685
• —eval_wer: 56.4808
• —evalshonawer: 36.8120
• —evalshonaloss: 0.4379
• —evaltshivendawer: 76.1495
• —evaltshivendaloss: 0.8991
• —epoch: 8.8183
• —step: 20000

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: 16
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 100
• —training_steps: 20000
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 5.15.0
• —Pytorch 2.13.0+cu130
• —Datasets 5.0.1
• —Tokenizers 0.22.2