rogramss/whisper-tiny_to_british_accent_ae_further_analysis

<!-- 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 British

This model is a fine-tuned version of openai/whisper-tiny on the British English 'AE' Phonemes dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.3636
• —eval_wer: 13.2631
• —eval_runtime: 140.0191
• —evalsamplesper_second: 3.392
• —evalstepsper_second: 3.392
• —epoch: 2.5
• —step: 1500

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: 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: 500
• —training_steps: 2000

Framework versions

• —Transformers 4.48.3
• —Pytorch 2.6.0+cu124
• —Datasets 3.4.1
• —Tokenizers 0.21.1