---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-ks
  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. -->

# wav2vec2-base-finetuned-ks

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1135
- Accuracy: 0.3403

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.2574        | 0.99  | 40   | 2.1881          | 0.2917   |
| 2.1367        | 1.99  | 80   | 2.1433          | 0.2917   |
| 2.1535        | 2.99  | 120  | 2.1255          | 0.2917   |
| 2.159         | 3.99  | 160  | 2.1135          | 0.3403   |
| 2.1341        | 4.99  | 200  | 2.1027          | 0.3403   |


### Framework versions

- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1