---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: facebook_wav2vec2-base
  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. -->

# facebook_wav2vec2-base

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4228
- Accuracy: 0.8974

## 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: 2
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.352         | 0.25  | 100  | 0.0266          | 0.9961   |
| 0.2689        | 0.5   | 200  | 0.2177          | 0.9808   |
| 1.2723        | 0.76  | 300  | 0.0354          | 0.9924   |
| 0.6624        | 1.01  | 400  | 0.4243          | 0.8974   |
| 0.5959        | 1.26  | 500  | 0.4805          | 0.8974   |
| 0.594         | 1.51  | 600  | 0.4401          | 0.8974   |
| 0.6017        | 1.76  | 700  | 0.4308          | 0.8974   |
| 0.5973        | 2.02  | 800  | 0.3904          | 0.8974   |
| 0.6096        | 2.27  | 900  | 0.4004          | 0.8974   |
| 0.5936        | 2.52  | 1000 | 0.4180          | 0.8974   |
| 0.5932        | 2.77  | 1100 | 0.4600          | 0.8974   |
| 0.5884        | 3.02  | 1200 | 0.4335          | 0.8974   |
| 0.5815        | 3.28  | 1300 | 0.3711          | 0.8974   |
| 0.5923        | 3.53  | 1400 | 0.4266          | 0.8974   |
| 0.6062        | 3.78  | 1500 | 0.4494          | 0.8974   |
| 0.6025        | 4.03  | 1600 | 0.4098          | 0.8974   |
| 0.5907        | 4.28  | 1700 | 0.3796          | 0.8974   |
| 0.5933        | 4.54  | 1800 | 0.4114          | 0.8974   |
| 0.5997        | 4.79  | 1900 | 0.4284          | 0.8974   |
| 0.6028        | 5.04  | 2000 | 0.4269          | 0.8974   |
| 0.5936        | 5.29  | 2100 | 0.4423          | 0.8974   |
| 0.5994        | 5.55  | 2200 | 0.4397          | 0.8974   |
| 0.5937        | 5.8   | 2300 | 0.4305          | 0.8974   |
| 0.5958        | 6.05  | 2400 | 0.4338          | 0.8974   |
| 0.5984        | 6.3   | 2500 | 0.3945          | 0.8974   |
| 0.5943        | 6.55  | 2600 | 0.3878          | 0.8974   |
| 0.5819        | 6.81  | 2700 | 0.4235          | 0.8974   |
| 0.594         | 7.06  | 2800 | 0.4160          | 0.8974   |
| 0.5883        | 7.31  | 2900 | 0.4076          | 0.8974   |
| 0.5877        | 7.56  | 3000 | 0.4213          | 0.8974   |
| 0.5939        | 7.81  | 3100 | 0.4089          | 0.8974   |
| 0.6025        | 8.07  | 3200 | 0.4385          | 0.8974   |
| 0.6016        | 8.32  | 3300 | 0.4373          | 0.8974   |
| 0.5815        | 8.57  | 3400 | 0.4191          | 0.8974   |
| 0.5915        | 8.82  | 3500 | 0.4216          | 0.8974   |
| 0.602         | 9.07  | 3600 | 0.4337          | 0.8974   |
| 0.5907        | 9.33  | 3700 | 0.4129          | 0.8974   |
| 0.603         | 9.58  | 3800 | 0.4216          | 0.8974   |
| 0.593         | 9.83  | 3900 | 0.4227          | 0.8974   |


### Framework versions

- Transformers 4.34.0.dev0
- Pytorch 2.0.0.post302
- Datasets 2.14.5
- Tokenizers 0.13.3