---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-wakeword
  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-wakeword

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: 4.0217
- Accuracy: 0.7473

## 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 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 7.269         | 0.9832 | 44   | 6.9029          | 0.5275   |
| 6.1201        | 1.9888 | 89   | 5.6800          | 0.5573   |
| 4.9094        | 2.9944 | 134  | 4.6621          | 0.6797   |
| 4.2402        | 4.0    | 179  | 4.0217          | 0.7473   |
| 3.8857        | 4.9162 | 220  | 3.8197          | 0.7174   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1