rossevine's picture
update model card README.md
6794870
|
raw
history blame
1.85 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Model_G_S_P_Wav2Vec2
    results: []

Model_G_S_P_Wav2Vec2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5098
  • Wer: 0.5366
  • Cer: 0.2277

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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Wer Cer
1.0449 3.49 400 1.7576 0.6270 0.2607
0.484 6.99 800 1.8072 0.6043 0.2536
0.3335 10.48 1200 2.0222 0.5892 0.2500
0.2559 13.97 1600 2.4174 0.5719 0.2448
0.1999 17.47 2000 2.2888 0.5566 0.2376
0.1546 20.96 2400 2.5271 0.5753 0.2400
0.1225 24.45 2800 2.4489 0.5427 0.2327
0.0983 27.95 3200 2.5098 0.5366 0.2277

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3