Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,12 @@ pipeline_tag: automatic-speech-recognition
|
|
| 25 |
This model is **one of the very few publicly available systems** explicitly optimized for:
|
| 26 |
- Egyptian Arabic dialect transcription
|
| 27 |
- Natural Arabic ↔ English code-switching
|
| 28 |
-
- Short and medium-length real-world audio
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
---
|
| 31 |
|
|
|
|
| 25 |
This model is **one of the very few publicly available systems** explicitly optimized for:
|
| 26 |
- Egyptian Arabic dialect transcription
|
| 27 |
- Natural Arabic ↔ English code-switching
|
| 28 |
+
- Short and medium-length real-world audio
|
| 29 |
+
|
| 30 |
+
The model is trained using:
|
| 31 |
+
- **MohamedRashad/arabic-english-code-switching** dataset
|
| 32 |
+
- **A private Egyptian speech dataset** containing real conversational audio, voice notes, and mixed Arabic/English speech recordings
|
| 33 |
+
|
| 34 |
|
| 35 |
---
|
| 36 |
|