---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
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: 0.4572
- Wer: 0.3320

## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2182        | 4.0   | 500  | 0.3727          | 0.3821 |
| 0.1352        | 8.0   | 1000 | 0.4079          | 0.3818 |
| 0.0992        | 12.0  | 1500 | 0.4380          | 0.3579 |
| 0.07          | 16.0  | 2000 | 0.4601          | 0.3466 |
| 0.0514        | 20.0  | 2500 | 0.4377          | 0.3408 |
| 0.0363        | 24.0  | 3000 | 0.4464          | 0.3368 |
| 0.0295        | 28.0  | 3500 | 0.4572          | 0.3320 |


### Framework versions

- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 1.18.3
- Tokenizers 0.21.2