whisper-small-sein / README.md
Cristhian2430's picture
End of training
5f56881
metadata
language:
  - es
license: apache-2.0
base_model: openai/whisper-large
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Large SEIN - COES SEIN
    results: []

Whisper Large SEIN - COES SEIN

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

  • Loss: 2.4838
  • Wer: 90.3132

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: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss Wer
3.0425 5.0 25 2.9421 95.1647
2.7073 10.0 50 2.4838 90.3132

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3