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

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4049
- Wer: 0.3556

## 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: 8
- 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: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 2.7319        | 1.0   | 500  | 1.3558          | 0.8890 |
| 0.7826        | 2.01  | 1000 | 0.5655          | 0.5398 |
| 0.4157        | 3.01  | 1500 | 0.4692          | 0.4682 |
| 0.2722        | 4.02  | 2000 | 0.4285          | 0.4193 |
| 0.2094        | 5.02  | 2500 | 0.4170          | 0.3949 |
| 0.1682        | 6.02  | 3000 | 0.3895          | 0.3751 |
| 0.1295        | 7.03  | 3500 | 0.3943          | 0.3628 |
| 0.1064        | 8.03  | 4000 | 0.4198          | 0.3648 |
| 0.0869        | 9.04  | 4500 | 0.4049          | 0.3556 |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.11.0+cu113
- Datasets 1.18.3
- Tokenizers 0.12.1