Update README.md
Browse files
README.md
CHANGED
|
@@ -9,4 +9,66 @@ pipeline_tag: text-classification
|
|
| 9 |
datasets:
|
| 10 |
- Msobhi/virgool_62k
|
| 11 |
---
|
| 12 |
-
Hi
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
datasets:
|
| 10 |
- Msobhi/virgool_62k
|
| 11 |
---
|
| 12 |
+
Hi
|
| 13 |
+
|
| 14 |
+
I have fine-tuned ParsBert for classifying Persian text using the "Msobhi/virgool_62k" dataset, with the labels listed below:
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
{'استارتاپ': 0,
|
| 18 |
+
'اقتصاد': 1,
|
| 19 |
+
'امنیت سایبری': 2,
|
| 20 |
+
'اینترنت اشیا': 3,
|
| 21 |
+
'بازاریابی': 4,
|
| 22 |
+
'بازی رایانه ای': 5,
|
| 23 |
+
'برنامه نویسی': 6,
|
| 24 |
+
'بلاک چین': 7,
|
| 25 |
+
'بهره وری': 8,
|
| 26 |
+
'تاریخ': 9,
|
| 27 |
+
'تجربه کاربری': 10,
|
| 28 |
+
'تحصیلی و آموزشی': 11,
|
| 29 |
+
'حقوقی': 12,
|
| 30 |
+
'خانواده': 13,
|
| 31 |
+
'خودشناسی': 14,
|
| 32 |
+
'داستان': 15,
|
| 33 |
+
'رابطه': 16,
|
| 34 |
+
'روانشناسی': 17,
|
| 35 |
+
'زنان': 18,
|
| 36 |
+
'سفر': 19,
|
| 37 |
+
'سلامت': 20,
|
| 38 |
+
'سلامت روانی': 21,
|
| 39 |
+
'سیاست': 22,
|
| 40 |
+
'شبکه اجتماعی': 23,
|
| 41 |
+
'شغل و کار': 24,
|
| 42 |
+
'طراحی دیجیتال': 25,
|
| 43 |
+
'علوم': 26,
|
| 44 |
+
'عکاسی': 27,
|
| 45 |
+
'غذا': 28,
|
| 46 |
+
'فرهنگ': 29,
|
| 47 |
+
'فریلنسری': 30,
|
| 48 |
+
'فلسفه': 31,
|
| 49 |
+
'فیلم و سینما': 32,
|
| 50 |
+
'فین تک': 33,
|
| 51 |
+
'محیط زیست': 34,
|
| 52 |
+
'مذهبی': 35,
|
| 53 |
+
'مهاجرت': 36,
|
| 54 |
+
'مهندسی نرم افزار': 37,
|
| 55 |
+
'موسیقی': 38,
|
| 56 |
+
'موفقیت': 39,
|
| 57 |
+
'نویسندگی': 40,
|
| 58 |
+
'هنر': 41,
|
| 59 |
+
'هوا فضا': 42,
|
| 60 |
+
'هوش مصنوعی': 43,
|
| 61 |
+
'ورزشی': 44,
|
| 62 |
+
'پادکست': 45,
|
| 63 |
+
'پول رمزی': 46,
|
| 64 |
+
'کارآفرینی': 47,
|
| 65 |
+
'کتاب': 48,
|
| 66 |
+
'یادگیری ماشین': 49}
|
| 67 |
+
|
| 68 |
+
Utilize this code snippet to test the model. It may not be very accurate, but further training epochs could enhance its performance.
|
| 69 |
+
|
| 70 |
+
model_path = "Aminrhmni/Persian-text-classification-model"
|
| 71 |
+
from transformers import pipeline, BertForSequenceClassification, BertTokenizerFast
|
| 72 |
+
model = BertForSequenceClassification.from_pretrained(model_path)
|
| 73 |
+
tokenizer= BertTokenizerFast.from_pretrained(model_path)
|
| 74 |
+
nlp= pipeline("text-classification", model=model, tokenizer=tokenizer)
|