Automatic Speech Recognition
Transformers
Safetensors
Arabic
wav2vec2-bert
audio-frame-classification
Generated from Trainer
arabic
quran
speech-segmentation
Instructions to use obadx/recitation-segmenter-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use obadx/recitation-segmenter-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="obadx/recitation-segmenter-v2")# Load model directly from transformers import AutoProcessor, AutoModelForAudioFrameClassification processor = AutoProcessor.from_pretrained("obadx/recitation-segmenter-v2") model = AutoModelForAudioFrameClassification.from_pretrained("obadx/recitation-segmenter-v2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "test__loss": 0.027765216305851936, | |
| "test__accuracy": 0.9934870571037636, | |
| "test__precision": 0.9936779395047649, | |
| "test__recall": 0.9958542244633207, | |
| "test__f1": 0.9947648917001393, | |
| "test__runtime": 409.2392, | |
| "test__samples_per_second": 21.472, | |
| "test__steps_per_second": 0.337, | |
| "epoch": 1.0 | |
| } |