---
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilhubert-finetuned-cry-detector
  results:
  - task:
      name: Audio Classification
      type: audio-classification
    dataset:
      name: audiofolder
      type: audiofolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9852941176470589
    - name: F1
      type: f1
      value: 0.9853150765112866
    - name: Precision
      type: precision
      value: 0.9853868369053048
    - name: Recall
      type: recall
      value: 0.9852941176470589
---

<!-- 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. -->

# distilhubert-finetuned-cry-detector

This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0332
- Accuracy: 0.9853
- F1: 0.9853
- Precision: 0.9854
- Recall: 0.9853

## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 123
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 10

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| No log        | 0.9412 | 12   | 0.1931          | 0.9363   | 0.9365 | 0.9372    | 0.9363 |
| No log        | 1.9608 | 25   | 0.0950          | 0.9706   | 0.9704 | 0.9710    | 0.9706 |
| No log        | 2.9804 | 38   | 0.0611          | 0.9804   | 0.9804 | 0.9804    | 0.9804 |
| No log        | 4.0    | 51   | 0.0492          | 0.9853   | 0.9853 | 0.9853    | 0.9853 |
| No log        | 4.9412 | 63   | 0.0588          | 0.9804   | 0.9805 | 0.9814    | 0.9804 |
| No log        | 5.9608 | 76   | 0.0368          | 0.9853   | 0.9853 | 0.9854    | 0.9853 |
| No log        | 6.9804 | 89   | 0.0382          | 0.9902   | 0.9902 | 0.9903    | 0.9902 |
| No log        | 8.0    | 102  | 0.0318          | 0.9951   | 0.9951 | 0.9951    | 0.9951 |
| No log        | 8.9412 | 114  | 0.0331          | 0.9853   | 0.9853 | 0.9854    | 0.9853 |
| No log        | 9.4118 | 120  | 0.0332          | 0.9853   | 0.9853 | 0.9854    | 0.9853 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1