metadata
language:
- ar
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- ymoslem/MediaSpeech
- UBC-NLP/Casablanca
- mozilla-foundation/common_voice_17_0
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Medium ar
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: ymoslem/MediaSpeech
config: ar
split: test
args: ar
metrics:
- name: Wer
type: wer
value: 15.325045470739346
Whisper Medium ar
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.4504
- Wer: 15.3250
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: 8
- 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: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2423 | 0.2 | 1000 | 2.0205 | 21.3178 |
| 0.0667 | 0.4 | 2000 | 2.3750 | 18.2033 |
| 0.047 | 0.6 | 3000 | 2.4276 | 17.5658 |
| 0.0249 | 0.8 | 4000 | 2.7231 | 16.1576 |
| 0.017 | 1.0 | 5000 | 2.4504 | 15.3250 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
Citation
@misc{deepdml/whisper-medium-ar-mix-norm,
title={Fine-tuned Whisper medium ASR model for speech recognition in Arabic},
author={Jimenez, David},
howpublished={\url{https://huggingface.co/deepdml/whisper-medium-ar-mix-norm}},
year={2025}
}