---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: neunit-ks-20230509V3
  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. -->

# neunit-ks-20230509V3

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1696
- Accuracy: 0.9816

## 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-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5857        | 0.99  | 53   | 0.4074          | 0.9329   |
| 0.2251        | 2.0   | 107  | 0.1696          | 0.9816   |
| 0.1465        | 2.99  | 160  | 0.1284          | 0.975    |
| 0.1169        | 4.0   | 214  | 0.0939          | 0.9803   |
| 0.1153        | 4.95  | 265  | 0.0930          | 0.9789   |


### Framework versions

- Transformers 4.29.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3