---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-base-timit-demo-colab-1
  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-timit-demo-colab-1

This model is a fine-tuned version of [zasheza/wav2vec2-base-timit-demo-colab-1](https://huggingface.co/zasheza/wav2vec2-base-timit-demo-colab-1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8811
- Wer: 0.4169

## 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: 6
- 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: 800
- num_epochs: 40
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.161         | 5.26  | 500  | 0.7465          | 0.4496 |
| 0.1852        | 10.53 | 1000 | 0.8108          | 0.4739 |
| 0.1457        | 15.79 | 1500 | 0.9073          | 0.4600 |
| 0.1073        | 21.05 | 2000 | 0.8817          | 0.4486 |
| 0.085         | 26.32 | 2500 | 0.9262          | 0.4442 |
| 0.0753        | 31.58 | 3000 | 0.8838          | 0.4337 |
| 0.0647        | 36.84 | 3500 | 0.8811          | 0.4169 |


### Framework versions

- Transformers 4.11.3
- Pytorch 1.11.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3