---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: ArabicSpeechToText
  results: []
language:
- ar
---

<!-- 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. -->

# ArabicSpeechToText

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3207
- Wer: 0.2901

## 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: 0.0003
- train_batch_size: 2
- eval_batch_size: 8
- seed: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 5.6589        | 0.52  | 700  | 0.8361          | 0.7598 |
| 0.7367        | 1.03  | 1400 | 0.5243          | 0.4771 |
| 0.479         | 1.55  | 2100 | 0.4025          | 0.3756 |
| 0.3742        | 2.06  | 2800 | 0.3651          | 0.3272 |
| 0.2846        | 2.58  | 3500 | 0.3207          | 0.2901 |


### Framework versions

- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 2.9.0
- Tokenizers 0.10.3