Skip to content
ModelListedExternal
Download

Ast Finetuned Audioset 10 10 0.4593 Finetuned Gtzan

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set: Loss: 0.7946 Accuracy: 0.86 Macro F1: 0.8497

Sourcehuggingface.co/ravalikuchibhotla/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan/tree/dc6df56776c9c874e2ab4ea688481ac36444798f
KindOtherBase modelMIT/ast-finetuned-audioset-10-10-0.4593VersionRevision dc6df56

Model source

Kind
Other
File size
329 MB
Base model
MIT/ast-finetuned-audioset-10-10-0.4593
Version
vRevision dc6df56
Updated
Sep 19, 2026
Downloads
18
Source
Hugging Face

Source description

ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan-multi-1

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

  • Loss: 0.7946
  • Accuracy: 0.86
  • Macro F1: 0.8497

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-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 15
  • mixed_precision_training: Native AMP
  • label_smoothing_factor: 0.1

Training results

Training LossEpochStepValidation LossAccuracyMacro F1
1.62241.01021.62000.68890.6797
1.07202.02041.01570.82220.8062
0.89213.03060.91690.82220.7936
0.73854.04080.87930.83330.8205
0.73135.05100.88630.80.7725
0.56276.06120.87600.82220.8113
0.67727.07140.87350.83330.8204
0.53888.08160.87050.82220.8125
0.52269.09180.86980.82220.8111
0.606310.010200.87480.82220.8099
0.516311.011220.87570.83330.8246
0.530012.012240.86840.83330.8251
0.514513.013260.86600.83330.8217
0.508214.014280.86630.82220.8098
0.509915.015300.86580.83330.8246

Framework versions

  • Transformers 5.0.1.dev0
  • Pytorch 2.9.0+cu126
  • Datasets 3.6.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrimaryVersion dc6df56776c9c874e2ab4ea688481ac36444798f
huggingface.co/ravalikuchibhotla/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan/tree/dc6df56776c9c874e2ab4ea688481ac36444798f

Verified Sep 19

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 261cf9aea0fd…54db · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 19huggingface.co/ravalikuchibhotla/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

--- library_name: transformers license: bsd-3-clause base_model: MIT/ast-finetuned-audioset-10-10-0.4593 tags: - generated_from_trainer datasets: - marsyas/gtzan metrics: - accuracy model-index: - name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan-multi-1 results: - task: name: Audio Classification type: audio-classification dataset: name: GTZAN type: marsyas/gtzan config: all split: train args: all metrics: - name: Accuracy type: accuracy value: 0.86 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan-multi-1 This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset. It achieves the following results on the evaluation set: - Loss: 0.7946 - Accuracy: 0.86 - Macro F1: 0.8497 ## 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-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 15 - mixed_precision_training: Native AMP - label_smoothing_factor: 0.1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:| | 1.6224 | 1.0 | 102 | 1.6200 | 0.6889 | 0.6797 | | 1.0720 | 2.0 | 204 | 1.0157 | 0.8222 | 0.8062 | | 0.8921 | 3.0 | 306 | 0.9169 | 0.8222 | 0.7936 | | 0.7385 | 4.0 | 408 | 0.8793 | 0.8333 | 0.8205 | | 0.7313 | 5.0 | 510 | 0.8863 | 0.8 | 0.7725 | | 0.5627 | 6.0 | 612 | 0.8760 | 0.8222 | 0.8113 | | 0.6772 | 7.0 | 714 | 0.8735 | 0.8333 | 0.8204 | | 0.5388 | 8.0 | 816 | 0.8705 | 0.8222 | 0.8125 | | 0.5226 | 9.0 | 918 | 0.8698 | 0.8222 | 0.8111 | | 0.6063 | 10.0 | 1020 | 0.8748 | 0.8222 | 0.8099 | | 0.5163 | 11.0 | 1122 | 0.8757 | 0.8333 | 0.8246 | | 0.5300 | 12.0 | 1224 | 0.86...

NoteSep 19huggingface.co/ravalikuchibhotla/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

Source context: 18 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo ravalikuchibhotla/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan