You can deploy this model and start earning money today!

mansoorSaleh/
whisper-yemeni

Name: whisper-yemeni
Availability: InStock

safetensors

whisper

automatic-speech-recognition

yemeni-arabic

openai/whisper-large-v2

finetune

cc-by-nc-sa-4.0

Views

No views yet

Whisper-Yemeni — Yemeni Arabic ASR (AYDID)

openai/whisper-large-v2 fine-tuned on the AYDID corpus for Yemeni Arabic speech recognition across seven sub-dialects (Adeni, Badawi, Hadrami, Sana'ani, Ta'izzi, Tihami, Standard Yemeni).

Base model: openai/whisper-large-v2
Dataset: mansoorSaleh/AYDID
Task: automatic speech recognition

Result

In-domain fine-tuning cuts normalized WER+ from the best zero-shot system's 43.92% to 19.14% overall — a 24.8-point reduction. Per sub-dialect:

Dialect	Whisper L-V3 (zero-shot)	Whisper-Yemeni
Adeni (YEM_AD)	46.47	16.65
Badawi (YEM_BA)	78.38	19.27
Hadrami (YEM_HA)	42.78	31.78
Sana'ani (YEM_SA)	51.69	19.34
Standard (YEM_ST)	24.77	13.51
Ta'izzi (YEM_TA)	42.86	14.38
Tihami (YEM_TI)	49.57	19.13
Overall	43.92	19.14

WER+ = normalized (punctuation and diacritics removed). Hadrami is hardest, consistent with its distinctive /q/→/g/ realisation; Standard Yemeni is easiest, reflecting MSA proximity.

Usage

python

import librosa
from transformers import WhisperProcessor, WhisperForConditionalGeneration

model_id = "mansoorSaleh/whisper-yemeni"
processor = WhisperProcessor.from_pretrained(model_id)
model = WhisperForConditionalGeneration.from_pretrained(model_id).eval()

wav, _ = librosa.load("clip.wav", sr=16000)
inputs = processor(wav, sampling_rate=16000, return_tensors="pt")
ids = model.generate(inputs.input_features, language="ar", task="transcribe")
print(processor.batch_decode(ids, skip_special_tokens=True)[0])

Citation

bibtex

@inproceedings{aydid2027,
  title     = {AYDID: A Sub-Dialectal Yemeni Arabic Corpus for Dialect
               Identification and Speech Recognition},
  author    = {Ba Mahel, Mansoor S. M. and Wei, Jianguo and Yue, Xianghu and
               Awn, Norah Saeed and Bamahel, Abdulaziz S.},
  booktitle = {Proc. IEEE ICASSP},
  year      = {2027}
}

License: CC BY-NC-SA 4.0 (research use).