jonastokoliu's picture
update model card README.md
707c6f4
metadata
tags:
  - generated_from_trainer
datasets:
  - minds14
metrics:
  - accuracy
model-index:
  - name: audio_cls_wavlm-libri-clean-100h-base-plus_minds14_finetune
    results: []

audio_cls_wavlm-libri-clean-100h-base-plus_minds14_finetune

This model is a fine-tuned version of patrickvonplaten/wavlm-libri-clean-100h-base-plus on the minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6462
  • Accuracy: 0.0708

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: 3e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 2 2.6464 0.0885
No log 2.0 4 2.6503 0.0442
No log 3.0 6 2.6485 0.0619
No log 4.0 8 2.6484 0.0708
2.6352 5.0 10 2.6473 0.0708
2.6352 6.0 12 2.6476 0.0708
2.6352 7.0 14 2.6473 0.0708
2.6352 8.0 16 2.6466 0.0708
2.6352 9.0 18 2.6462 0.0708
2.6349 10.0 20 2.6462 0.0708

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3