---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: tericvoices_luganda
  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. -->

# tericvoices_luganda

This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4047
- Wer: 0.5150

## 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: 0.0005
- train_batch_size: 16
- 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: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 3.3976        | 0.9   | 1000 | 0.7300          | 0.8515 |
| 0.5609        | 1.81  | 2000 | 0.5297          | 0.6709 |
| 0.4076        | 2.71  | 3000 | 0.4736          | 0.5962 |
| 0.3255        | 3.61  | 4000 | 0.4087          | 0.5310 |
| 0.2666        | 4.52  | 5000 | 0.4047          | 0.5150 |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0