Skip to content
ModelListedExternal
Download

Red Round Button Small Click Detector N25

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: 0.1324 Recall Pressed: 0.8921 Precision Pressed:...

Sourcehuggingface.co/ramen-noodels/red_round_button_small_click_detector_n25/tree/b443bfaa02992fe39b31ef5ed5dcb13eb9bc8d86
KindOtherBase modelMIT/ast-finetuned-audioset-10-10-0.4593VersionRevision b443bfaBgrade

Model source

Kind
Other
File size
326 MB
Base model
MIT/ast-finetuned-audioset-10-10-0.4593
Version
vRevision b443bfa
Updated
Oct 31, 2026
Downloads
7
Source
Hugging Face

Source description

red_round_button_small_click_detector_n25

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: 0.1324
  • Recall Pressed: 0.8921
  • Precision Pressed: 0.9094
  • F1 Pressed: 0.9006
  • False Negative Rate: 0.1079

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
0.02361.0870.08580.83170.98870.90340.1683
0.02342.01740.07250.91750.88110.89890.0825
0.01533.02610.09020.84440.95680.89710.1556
0.00404.03480.11900.92380.88990.90650.0762
0.01175.04350.11190.88570.91780.90150.1143
0.00476.05220.12080.92060.89230.90620.0794
0.00507.06090.12420.89840.91000.90420.1016
0.00388.06960.12790.89840.91000.90420.1016
0.00019.07830.13190.89210.90940.90060.1079
0.002710.08700.13300.89210.90940.90060.1079

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion b443bfaa02992fe39b31ef5ed5dcb13eb9bc8d86
huggingface.co/ramen-noodels/red_round_button_small_click_detector_n25/tree/b443bfaa02992fe39b31ef5ed5dcb13eb9bc8d86

Verified Oct 31

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

model.safetensors

safetensors · FP32 (unverified) · 326 MB · SHA-256 037e2469d37c…c0da · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 15huggingface.co/ramen-noodels/red_round_button_small_click_detector_n25

--- 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_n25 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_n25 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: 0.1324 - Recall Pressed: 0.8921 - Precision Pressed: 0.9094 - F1 Pressed: 0.9006 - False Negative Rate: 0.1079 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:--------------:|:-----------------:|:----------:|:-------------------:| | 0.0236 | 1.0 | 87 | 0.0858 | 0.8317 | 0.9887 | 0.9034 | 0.1683 | | 0.0234 | 2.0 | 174 | 0.0725 | 0.9175 | 0.8811 | 0.8989 | 0.0825 | | 0.0153 | 3.0 | 261 | 0.0902 | 0.8444 | 0.9568 | 0.8971 | 0.1556 | | 0.0040 | 4.0 | 348 | 0.1190 | 0.9238 | 0.8899 | 0.9065 | 0.0762 | | 0.0117 | 5.0 | 435 | 0.1119 | 0.8857 | 0.9178 | 0.9015 | 0.1143 | | 0.0047 | 6.0 | 522 | 0.1208 | 0.9206 | 0.8923 | 0.9062 | 0.0794 | | 0.0050 | 7.0 | 609 | 0.1242 | 0.8984 | 0.9100 | 0.9042 | 0.1016 | | 0.0038 | 8.0 | 696 | 0.1279 | 0.8984 | 0.9100 | 0.9042 | 0.1016 | | 0.0001 | 9.0 | 783 | 0.1319 | 0.8921 | 0.9094 | 0.9006 | 0.1079 | | 0.0027 | 10.0 | 870 | 0.1330 | 0.8921 | 0.9094 | 0.9006 | 0.1079 | ### Framework versions - Transformers 5.11.0 - Pytorch 2.7.1+cu118 - Datasets 5.0.0 - Tokenizers 0.22.2

NoteOct 31huggingface.co/ramen-noodels/red_round_button_small_click_detector_n25

Source context: 7 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo ramen-noodels/red_round_button_small_click_detector_n25

NoteAug 15huggingface.co/ramen-noodels/red_round_button_small_click_detector_n25

Source context: 6 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo ramen-noodels/red_round_button_small_click_detector_n25