---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- vivos
metrics:
- wer
model-index:
- name: working
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: vivos
      type: vivos
      config: default
      split: None
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 0.20034507930187803
---

<!-- 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. -->

# working

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the vivos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2861
- Wer: 0.2003

## 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 5.8286        | 1.0274 | 300  | 3.6649          | 1.0    |
| 3.3501        | 2.0548 | 600  | 2.5006          | 0.9971 |
| 1.0597        | 3.0822 | 900  | 0.5530          | 0.3923 |
| 0.5399        | 4.1096 | 1200 | 0.4242          | 0.3123 |
| 0.4275        | 5.1370 | 1500 | 0.3533          | 0.2677 |
| 0.363         | 6.1644 | 1800 | 0.3392          | 0.2368 |
| 0.3145        | 7.1918 | 2100 | 0.3485          | 0.2331 |
| 0.2803        | 8.2192 | 2400 | 0.3139          | 0.2136 |
| 0.2551        | 9.2466 | 2700 | 0.2939          | 0.2065 |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1