whispherMusicTiny / README.md
nacielo's picture
update model card README.md
b9c4e3a
metadata
license: apache-2.0
base_model: openai/whisper-tiny.en
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: whispherMusicTiny
    results: []

whispherMusicTiny

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

  • Loss: 1.5623
  • Rouge1: 26.7441
  • Rouge2: 6.3706
  • Rougel: 23.6169
  • Rougelsum: 23.5887
  • Gen Len: 65.71

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.187 1.0 959 2.8591 22.3571 4.0074 20.7932 20.8063 67.11
2.4008 2.0 1918 2.3569 25.1707 4.7622 22.9043 22.934 59.9
2.059 3.0 2877 1.9763 23.6382 4.0133 21.9178 21.9638 57.94
1.7741 4.0 3836 1.6896 25.0574 5.335 22.7412 22.7141 64.13
1.542 5.0 4795 1.5623 26.7441 6.3706 23.6169 23.5887 65.71

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.2
  • Tokenizers 0.13.3