manushya-ai/whisper-medium-finetuned

<!-- 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-finetuned

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

• —eval_loss: 0.0120
• —eval_wer: 28.7151
• —eval_runtime: 98.274
• —evalsamplesper_second: 0.407
• —evalstepsper_second: 0.407
• —epoch: 9.0
• —step: 540

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: 2e-05
• —trainbatchsize: 2
• —evalbatchsize: 1
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 30
• —num_epochs: 10

Framework versions

• —Transformers 4.48.0
• —Pytorch 2.9.0+cu128
• —Datasets 4.4.1
• —Tokenizers 0.21.4