Automatic Speech Recognition
Transformers
Safetensors
Arabic
whisper
Arabic
AR
speech to text
stt
transcription
Eval Results (legacy)
Instructions to use YazanSalameh/Whisper-base-Arabic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YazanSalameh/Whisper-base-Arabic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="YazanSalameh/Whisper-base-Arabic")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("YazanSalameh/Whisper-base-Arabic") model = AutoModelForSpeechSeq2Seq.from_pretrained("YazanSalameh/Whisper-base-Arabic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ Train set:
|
|
| 42 |
- BelalElhossany/mgb2_audios_transcriptions_non_overlap
|
| 43 |
- nadsoft/Jordan-Audio
|
| 44 |
|
| 45 |
-
|
| 46 |
600 samples in total from the 3 sets to save time during training as colab free tier was used to train the model.
|
| 47 |
note: evaluate accuracy in the way you see fit.
|
| 48 |
|
|
|
|
| 42 |
- BelalElhossany/mgb2_audios_transcriptions_non_overlap
|
| 43 |
- nadsoft/Jordan-Audio
|
| 44 |
|
| 45 |
+
cross validation set:
|
| 46 |
600 samples in total from the 3 sets to save time during training as colab free tier was used to train the model.
|
| 47 |
note: evaluate accuracy in the way you see fit.
|
| 48 |
|