kiriku/whisper-large-v2-en-homophone

<!-- 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. -->

Homophonesfilteddataset Whisper large-v2 en

This model is a fine-tuned version of openai/whisper-small on the Homophones in Common Voice 15.0 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.1999
• —Wer: 17.2571

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: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 4000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.36.0.dev0
• —Pytorch 1.12.1+cu113
• —Datasets 2.15.0
• —Tokenizers 0.15.0