Update README.md
Browse files
README.md
CHANGED
|
@@ -2,10 +2,7 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags: []
|
| 4 |
---
|
| 5 |
-
|
| 6 |
-
<!-- # Arabic Tashkeel Generator -->
|
| 7 |
-
<!-- # Automatic Arabic Diacritics Generator -->
|
| 8 |
-
# ุชูุดูููููู ุงููููุตููุตู ุงููุนูุฑูุจููููุฉู ุชูููููุงุฆูููุงู
|
| 9 |
This model is trained to add tashkeel (Arabic diacritics) to Arabic text, enhancing readability and pronunciation. It may be also helpful for data synthesis training models on other tasks, such as text-to-speech, language modeling, and more.
|
| 10 |
|
| 11 |
## Model Details
|
|
@@ -24,7 +21,6 @@ model_path = "Abdou/arabic-tashkeel-flan-t5-small"
|
|
| 24 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 25 |
model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
|
| 26 |
|
| 27 |
-
# both above functions on a single function
|
| 28 |
def vocalize_text(text, model, tokenizer, max_length=256, num_beams=4, temperature=0.2, do_sample=False):
|
| 29 |
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 30 |
model.to(device)
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags: []
|
| 4 |
---
|
| 5 |
+
# ุชูุดูููููู ุงููููุตููุตู ุงููุนูุฑูุจููููุฉู ุชูููููุงุฆููุงู
|
|
|
|
|
|
|
|
|
|
| 6 |
This model is trained to add tashkeel (Arabic diacritics) to Arabic text, enhancing readability and pronunciation. It may be also helpful for data synthesis training models on other tasks, such as text-to-speech, language modeling, and more.
|
| 7 |
|
| 8 |
## Model Details
|
|
|
|
| 21 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 22 |
model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
|
| 23 |
|
|
|
|
| 24 |
def vocalize_text(text, model, tokenizer, max_length=256, num_beams=4, temperature=0.2, do_sample=False):
|
| 25 |
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 26 |
model.to(device)
|