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
Best checkpoint: step-1500 (CER=0.6922%, WER=3.2801%) — replaces step-2000 which overfit
Browse files- model.safetensors +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e51ce73a9a139da54fd5efa06599e8cbf96ecaa03b5e78d69d7460bdbddbdd4d
|
| 3 |
size 966995080
|