Automatic Speech Recognition
Transformers
PyTorch
JAX
Arabic
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use mohammed/arabic-speech-recognition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mohammed/arabic-speech-recognition with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mohammed/arabic-speech-recognition")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("mohammed/arabic-speech-recognition") model = AutoModelForCTC.from_pretrained("mohammed/arabic-speech-recognition") - Notebooks
- Google Colab
- Kaggle
| {"ع": 1, "ل": 2, "ﻻ": 3, "ی": 4, "ظ": 5, "ص": 6, "ز": 7, "ة": 8, "و": 9, "ک": 10, "ح": 11, "غ": 12, "ن": 13, "ﺃ": 14, "ت": 15, "ش": 16, "ب": 17, "أ": 18, "ه": 19, "ج": 20, "ئ": 21, "آ": 22, "ھ": 23, "ك": 24, "إ": 25, "ط": 26, "خ": 27, "چ": 28, "ى": 29, "د": 30, "ر": 31, "ء": 32, "ا": 33, "ف": 34, "ڨ": 35, "ؤ": 36, "ۚ": 37, "س": 38, "ق": 39, "ۖ": 40, "ذ": 41, "ي": 42, "م": 43, "ث": 44, "ض": 45, "|": 0, "[UNK]": 46, "[PAD]": 47} |