Instructions to use YHZDigital/wav2vec2-arabic-align-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use YHZDigital/wav2vec2-arabic-align-onnx with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('automatic-speech-recognition', 'YHZDigital/wav2vec2-arabic-align-onnx');
wav2vec2-large-xlsr-53-arabic (fp16 ONNX)
ONNX (float16) export of jonatasgrosman/wav2vec2-large-xlsr-53-arabic (Apache-2.0, by Jonatas Grosman), used in the browser for word-level forced alignment of Quran recitation (the same model WhisperX uses for Arabic). Changes: exported with torch.onnx (opset 17) and converted to fp16; weights otherwise unchanged.
- Downloads last month
- 62
Model tree for YHZDigital/wav2vec2-arabic-align-onnx
Base model
jonatasgrosman/wav2vec2-large-xlsr-53-arabic