---
language:
- ar
license: apache-2.0
base_model: openai/whisper-medium
tags:
- nadsoft
- generated_from_trainer
datasets:
- nadsoft/arabic-98
metrics:
- wer
model-index:
- name: ./hamsa-v0.6Q
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: nadsoft/arabic-98
      type: nadsoft/arabic-98
    metrics:
    - name: Wer
      type: wer
      value: 23.412419116812348
---

<!-- 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. -->

# ./hamsa-v0.6Q

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the nadsoft/arabic-98 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2781
- Wer: 23.4124

## 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: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- 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: 300
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.9225        | 0.33  | 100  | 0.8743          | 24.5136 |
| 0.2721        | 0.67  | 200  | 0.2782          | 24.1367 |
| 0.2474        | 1.0   | 300  | 0.2781          | 23.4124 |


### Framework versions

- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0