Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
arabic
quran
tashkeel
diacritics
tajweed
Eval Results (legacy)
Instructions to use NightPrince/stt-arabic-whisper-finetuned-diactires with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NightPrince/stt-arabic-whisper-finetuned-diactires with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NightPrince/stt-arabic-whisper-finetuned-diactires")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NightPrince/stt-arabic-whisper-finetuned-diactires") model = AutoModelForSpeechSeq2Seq.from_pretrained("NightPrince/stt-arabic-whisper-finetuned-diactires") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
Best checkpoint: step-1500 (CER=0.6922%, WER=3.2801%) — replaces step-2000 which overfit
edb614b verified