Ir para o conteúdo
ModelListadosExterno
Baixar

Red Round Button Small Click Detector N50

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: 0.1559 Recall Pressed: 0.8762 Precision Pressed:...

Fontehuggingface.co/ramen-noodels/red_round_button_small_click_detector_n50/tree/98b4ef9327e7a04bb268fdd6c88984d4c75f9d9b
TipoOtherModelo baseMIT/ast-finetuned-audioset-10-10-0.4593VersãoRevision 98b4ef9Bnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
326 MB
Modelo base
MIT/ast-finetuned-audioset-10-10-0.4593
Versão
vRevision 98b4ef9
Atualizado
31 de out. de 2026
Downloads
4
Fonte
Hugging Face

Descrição da fonte

red_round_button_small_click_detector_n50

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: 0.1559
  • Recall Pressed: 0.8762
  • Precision Pressed: 0.8932
  • F1 Pressed: 0.8846
  • False Negative Rate: 0.1238

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: 1e-05
  • train_batch_size: 82
  • eval_batch_size: 82
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training LossEpochStepValidation LossRecall PressedPrecision PressedF1 PressedFalse Negative Rate
0.02821.0580.05960.88890.92110.90470.1111
0.01262.01160.08550.96190.85350.90450.0381
0.00633.01740.07880.91750.87310.89470.0825
0.00374.02320.11320.88250.90260.89250.1175
0.00165.02900.12360.89520.88680.89100.1048
0.00026.03480.14560.86670.89800.88210.1333
0.00027.04060.15090.88570.89140.88850.1143
0.00028.04640.15450.88250.89100.88680.1175
0.00019.05220.15700.87940.89350.88640.1206
0.000110.05800.15760.87940.89350.88640.1206

Framework versions

  • Transformers 5.11.0
  • Pytorch 2.7.1+cu118
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Fontes

1 fonte
Hugging FacePrimárioVersão 98b4ef9327e7a04bb268fdd6c88984d4c75f9d9b
huggingface.co/ramen-noodels/red_round_button_small_click_detector_n50/tree/98b4ef9327e7a04bb268fdd6c88984d4c75f9d9b

Verificado 31 de out.

Download files

Repository files

File inventory only; completeness is unverified.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · FP32 (unverified) · 326 MB · SHA-256 f67671afda5d…e59d · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme15 de ago.huggingface.co/ramen-noodels/red_round_button_small_click_detector_n50

--- library_name: transformers license: bsd-3-clause base_model: MIT/ast-finetuned-audioset-10-10-0.4593 tags: - generated_from_trainer model-index: - name: red_round_button_small_click_detector_n50 results: [] --- <!-- 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. --> # red_round_button_small_click_detector_n50 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 an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1559 - Recall Pressed: 0.8762 - Precision Pressed: 0.8932 - F1 Pressed: 0.8846 - False Negative Rate: 0.1238 ## 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: 1e-05 - train_batch_size: 82 - eval_batch_size: 82 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Recall Pressed | Precision Pressed | F1 Pressed | False Negative Rate | |:-------------:|:-----:|:----:|:---------------:|:--------------:|:-----------------:|:----------:|:-------------------:| | 0.0282 | 1.0 | 58 | 0.0596 | 0.8889 | 0.9211 | 0.9047 | 0.1111 | | 0.0126 | 2.0 | 116 | 0.0855 | 0.9619 | 0.8535 | 0.9045 | 0.0381 | | 0.0063 | 3.0 | 174 | 0.0788 | 0.9175 | 0.8731 | 0.8947 | 0.0825 | | 0.0037 | 4.0 | 232 | 0.1132 | 0.8825 | 0.9026 | 0.8925 | 0.1175 | | 0.0016 | 5.0 | 290 | 0.1236 | 0.8952 | 0.8868 | 0.8910 | 0.1048 | | 0.0002 | 6.0 | 348 | 0.1456 | 0.8667 | 0.8980 | 0.8821 | 0.1333 | | 0.0002 | 7.0 | 406 | 0.1509 | 0.8857 | 0.8914 | 0.8885 | 0.1143 | | 0.0002 | 8.0 | 464 | 0.1545 | 0.8825 | 0.8910 | 0.8868 | 0.1175 | | 0.0001 | 9.0 | 522 | 0.1570 | 0.8794 | 0.8935 | 0.8864 | 0.1206 | | 0.0001 | 10.0 | 580 | 0.1576 | 0.8794 | 0.8935 | 0.8864 | 0.1206 | ### Framework versions - Transformers 5.11.0 - Pytorch 2.7.1+cu118 - Datasets 5.0.0 - Tokenizers 0.22.2

Note31 de out.huggingface.co/ramen-noodels/red_round_button_small_click_detector_n50

Source context: 4 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo ramen-noodels/red_round_button_small_click_detector_n50

Note15 de ago.huggingface.co/ramen-noodels/red_round_button_small_click_detector_n50

Source context: 7 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo ramen-noodels/red_round_button_small_click_detector_n50