MarekCech's picture
Update README.md
1b26b69 verified
metadata
metrics:
  - accuracy
pipeline_tag: audio-classification
tags:
  - music

This model is finetuned version of ntu-spml/distilhubert for music detection.

This model was finetuned to distinguish between music and non-music audio.

Training hyperparameters

The following hyperparameters were used during training:

  • metric_for_best_model = accuracy
  • learning_rate = 5e-5
  • seed = 42
  • per_device_train_batch_size = 4
  • per_device_eval_batch_size = 4
  • gradient_accumulation_steps = 1
  • warmup_ratio = 0.1
  • fp16 = True
  • adam_epsilon = 1e-08
  • adam_beta1 = 0.9
  • adam_beta2 = 0.999