AymanMansour/Whisper-Sudanese-Dialect-small

Sudanese Arabic(apd)ASRopenai/whisper-smallWhisperForConditionalGeneration

View Source

Model Info

Language

Sudanese Arabic (apd)

Architecture

WhisperForConditionalGeneration

Institution

Ayman Mansour (independent researcher)

Last Updated

22 May 2026

Intended Use Cases

Sudanese dialect ASR (WER 56.3% on eval set)

License & Access

SPDX identifierApache-2.0

Open — attribution required; commercial use allowed.

Provenance

Source URL

https://huggingface.co/AymanMansour/Whisper-Sudanese-Dialect-small

Fetch Timestamp

22 May 2026

Submitter

Ayman Mansour (independent researcher)

Full Record

22 of 25 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (16/18)

iso code: apd
Model Name: AymanMansour/Whisper-Sudanese-Dialect-small
Where is it hosted: HuggingFace
Link: https://huggingface.co/AymanMansour/Whisper-Sudanese-Dialect-small
Year: 2023
Creator/Author(s): Ayman Mansour (independent researcher)
Paper Reference: arXiv:2601.06802
NLP Task: ASR
Architecture: WhisperForConditionalGenerationderivedHugging Face config: architectures / model_type
Base Model: openai/whisper-small
Fine-tuned?: Yes
License: Apache-2.0
Open Access: Open
Has Model Card: Yes
SOTA Tasks: Sudanese dialect ASR (WER 56.3% on eval set)
Verified By: Not stated
Date Indexed: 2026-05-22
Comment: Not stated

Readiness (LRS) (6/7)

model id: aymanmansour-whisper-sudanese-dialect-small-apd
Model Type: ASRderivedHugging Face card: pipeline_tag
Training Data Sources: arbml/sudanese_dialect_speech + arabic_speech_corpus
Benchmark Used: SDN-Dialect-Dataset (Automatic Speech Recognition)derivedregistry benchmark records for this model
Benchmark Score: Wer: 56.3216
Benchmark Date: 2022
Status: Not stated