pere's picture
update model card README.md
ad566fd
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-NST-TPU-test2
    results: []

whisper-NST-TPU-test2

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

  • Loss: 4.9943
  • Wer: 100.0

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: tpu
  • num_devices: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 2

Training results

Training Loss Epoch Step Validation Loss Wer
5.535 1.0 2 4.9943 100.0

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.13.0+cu117
  • Datasets 2.6.1
  • Tokenizers 0.13.1