---
base_model: facebook/wav2vec2-base
datasets:
- timit_asr
library_name: transformers
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-base-timit-demo-colab
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: timit_asr
      type: timit_asr
      config: clean
      split: None
      args: clean
    metrics:
    - type: wer
      value: 0.3707532216938874
      name: Wer
---

<!-- 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

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the timit_asr dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4233
- Wer: 0.3708

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

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 3.5113        | 3.4483 | 500  | 1.1493          | 0.8214 |
| 0.554         | 6.8966 | 1000 | 0.4233          | 0.3708 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1