whisper-tiny-metal / README.md
jpdiazpardo's picture
End of training
4151aee
metadata
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Tiny Metal - Juan Pablo Diaz
    results: []

Whisper Tiny Metal - Juan Pablo Diaz

This model is a fine-tuned version of openai/whisper-tiny on the Gutural Scream and Metal Vocals dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6780
  • Wer: 79.9061

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: 4000

Training results

Training Loss Epoch Step Validation Loss Wer
0.0844 9.62 1000 1.3967 104.6055
0.0018 19.23 2000 1.5861 93.5465
0.0008 28.85 3000 1.6552 78.9381
0.0006 38.46 4000 1.6780 79.9061

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3