---
tags:
- audio-classification
- generated_from_trainer
datasets:
- superb
metrics:
- accuracy
model-index:
- name: trillsson3-ft-keyword-spotting-12
  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. -->

# trillsson3-ft-keyword-spotting-12

This model is a fine-tuned version of [vumichien/nonsemantic-speech-trillsson3](https://huggingface.co/vumichien/nonsemantic-speech-trillsson3) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2989
- Accuracy: 0.9169

## 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: 0.0003
- train_batch_size: 16
- eval_batch_size: 64
- seed: 0
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.2304        | 1.0   | 1597  | 0.7906          | 0.6845   |
| 0.8117        | 2.0   | 3194  | 0.4360          | 0.8673   |
| 0.7322        | 3.0   | 4791  | 0.3766          | 0.8844   |
| 0.7458        | 4.0   | 6388  | 0.3449          | 0.8986   |
| 0.7312        | 5.0   | 7985  | 0.3235          | 0.9135   |
| 0.7199        | 6.0   | 9582  | 0.3211          | 0.9059   |
| 0.72          | 7.0   | 11179 | 0.3263          | 0.9020   |
| 0.6992        | 8.0   | 12776 | 0.3186          | 0.9032   |
| 0.6543        | 9.0   | 14373 | 0.3116          | 0.9117   |
| 0.6346        | 10.0  | 15970 | 0.3176          | 0.9016   |
| 0.7189        | 11.0  | 17567 | 0.3116          | 0.9019   |
| 0.6628        | 12.0  | 19164 | 0.3072          | 0.9112   |
| 0.6855        | 13.0  | 20761 | 0.3162          | 0.9031   |
| 0.6651        | 14.0  | 22358 | 0.3047          | 0.9112   |
| 0.6962        | 15.0  | 23955 | 0.3005          | 0.9126   |
| 0.6348        | 16.0  | 25552 | 0.3110          | 0.9079   |
| 0.6595        | 17.0  | 27149 | 0.2989          | 0.9169   |
| 0.677         | 18.0  | 28746 | 0.3103          | 0.9098   |
| 0.6394        | 19.0  | 30343 | 0.3056          | 0.9085   |
| 0.6411        | 20.0  | 31940 | 0.3060          | 0.9089   |


### Framework versions

- Transformers 4.23.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1