addison_whisper / README.md
scanne's picture
Update README.md
6bd1f7f
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: addison_whisper
    results: []

addison_whisper

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

  • Loss: 0.5900
  • Wer: 31.0926

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
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0403 4.59 1000 0.5900 31.0926

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3