---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-base-timit-demo-colab90
  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-colab90

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: 0.6766
- Wer: 0.4479

## 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: 60
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 5.0217        | 7.04  | 500  | 3.2571          | 1.0    |
| 1.271         | 14.08 | 1000 | 0.6501          | 0.5874 |
| 0.4143        | 21.13 | 1500 | 0.5943          | 0.5360 |
| 0.2446        | 28.17 | 2000 | 0.6285          | 0.5028 |
| 0.1653        | 35.21 | 2500 | 0.6553          | 0.4992 |
| 0.1295        | 42.25 | 3000 | 0.6735          | 0.4705 |
| 0.1033        | 49.3  | 3500 | 0.6792          | 0.4539 |
| 0.0886        | 56.34 | 4000 | 0.6766          | 0.4479 |


### Framework versions

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