---
license: apache-2.0
base_model: openai/whisper-small
tags:
- audio
- automatic-speech-recognition
metrics:
- wer
widget:
  - example_title: Sample 1
    src: sample_ar_1.mp3
  - example_title: Sample 2
    src: sample_ar_2.mp3
model-index:
- name: whisper-small-ar-v2
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: common_voice_16_1
      type: common_voice_16_1
      config: ar
      split: test
      args: ar
    metrics:
    - name: Wer
      type: wer
      value: 47.726437288634024
language:
- ar
library_name: transformers
pipeline_tag: automatic-speech-recognition
datasets:
- mozilla-foundation/common_voice_16_1
---

<!-- 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. -->

# whisper-small-ar-v2

This model is for Arabic automatic speech recognition (ASR). It is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Arabic portion of the [mozilla-foundation/common_voice_16_1](https://huggingface.co/datasets/mozilla-foundation/common_voice_16_1) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4007
- Wer: 47.7264

## Model description

Whisper model fine-tuned on Arabic data, following the [official tutorial](https://huggingface.co/blog/fine-tune-whisper).

## Intended uses & limitations

It is recommended to fine-tune and evaluate on your data before using it.

## Training and evaluation data

Training Data: CommonVoice (v16.1) Arabic train + validation splits  
Validation Data: CommonVoice (v16.1) Arabic test split

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 8000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2742        | 0.82  | 1000 | 0.3790          | 275.2463 |
| 0.1625        | 1.65  | 2000 | 0.3353          | 228.5252 |
| 0.1002        | 2.47  | 3000 | 0.3311          | 238.8858 |
| 0.0751        | 3.3   | 4000 | 0.3354          | 158.1532 |
| 0.0601        | 4.12  | 5000 | 0.3576          | 48.9285  |
| 0.0612        | 4.95  | 6000 | 0.3575          | 47.8937  |
| 0.0383        | 5.77  | 7000 | 0.3819          | 46.9085  |
| 0.0234        | 6.6   | 8000 | 0.4007          | 47.7264  |


### Framework versions

- Transformers 4.38.1
- Pytorch 2.1.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2