metadata
language:
- ar
pipeline_tag: audio-classification
library_name: speechbrain
tags:
- DIalectID
- ADI
- ADI-20
- speechbrain
- Identification
- pytorch
- embeddings
datasets:
- ADI-20
metrics:
- f1
- precision
- recall
- accuracy
Install Requirements
SpeechBrain
First of all, please install SpeechBrain with the following command:
pip install git+https://github.com/speechbrain/speechbrain.git@develop
Clone ADI github repository
git clone https://github.com/elyadata/ADI-20
cd ADI-20
pip install -r requirements.txt
Perform Arabic Dialect Identification
from inference.classifier_attention_pooling import WhisperDialectClassifier
dialect_id = WhisperDialectClassifier.from_hparams(
source="",
hparams_file="hyperparms.yaml",
savedir="pretrained_DID/tmp").to("cuda")
dialect_id.device = "cuda"
dialect_id.classify_file("filenane.wav")
Citation
If using this work, please cite:
@inproceedings{elleuch2025adi20,
author = {Haroun Elleuch and Salima Mdhaffar and Yannick Estève and Fethi Bougares},
title = {ADI‑20: Arabic Dialect Identification Dataset and Models},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)},
year = {2025},
address = {Rotterdam Ahoy Convention Centre, Rotterdam, The Netherlands},
month = {August},
days = {17‑21}
}