metadata

library_name: transformers
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: romanian-dialects
    results: []

romanian-dialects

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6475
Accuracy: 0.7852
Precision: 0.7944
Recall: 0.7944
F1: 0.7901

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.343	1.0	217	1.3967	0.4088	0.2294	0.3723	0.2676
1.2531	2.0	434	1.0872	0.5150	0.6858	0.4909	0.4907
1.0475	3.0	651	1.0740	0.5219	0.6920	0.5005	0.4970
0.961	4.0	868	0.8763	0.6467	0.6808	0.6504	0.6587
0.9544	5.0	1085	0.9147	0.6351	0.6712	0.6401	0.6220
0.9991	6.0	1302	0.8161	0.6882	0.7471	0.6808	0.6952
0.7222	7.0	1519	0.7405	0.7044	0.7430	0.7117	0.7196
0.8498	8.0	1736	0.6856	0.7136	0.7309	0.7267	0.7262
0.6647	9.0	1953	0.6642	0.7529	0.7772	0.7553	0.7602
0.7179	10.0	2170	0.7459	0.7367	0.7712	0.7570	0.7483
0.6257	11.0	2387	0.6373	0.7460	0.7710	0.7496	0.7570
0.5433	12.0	2604	0.6549	0.7667	0.7744	0.7802	0.7738
0.3504	13.0	2821	0.6475	0.7852	0.7944	0.7944	0.7901
0.5599	14.0	3038	0.6033	0.7783	0.7831	0.7822	0.7819

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0