Spaces:
Build error
Build error
Commit ·
ee77aba
1
Parent(s): c6268df
updated README for spaces
Browse files- .gitignore +1 -2
- README.md +17 -1
.gitignore
CHANGED
|
@@ -3,5 +3,4 @@ __pycache__
|
|
| 3 |
test.csv
|
| 4 |
GPT2_encoder.py
|
| 5 |
Hindi_Regex.txt
|
| 6 |
-
Hindi_no_Regex.txt
|
| 7 |
-
text_file.txt
|
|
|
|
| 3 |
test.csv
|
| 4 |
GPT2_encoder.py
|
| 5 |
Hindi_Regex.txt
|
| 6 |
+
Hindi_no_Regex.txt
|
|
|
README.md
CHANGED
|
@@ -1,4 +1,20 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
## Dataset
|
| 4 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: Hindi BPE Tokenizer
|
| 3 |
+
emoji: 🇮🇳
|
| 4 |
+
colorFrom: orange
|
| 5 |
+
colorTo: green
|
| 6 |
+
sdk: streamlit
|
| 7 |
+
sdk_version: 1.32.0
|
| 8 |
+
app_file: app.py
|
| 9 |
+
pinned: false
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Hindi BPE Tokenizer
|
| 13 |
+
A Byte-Pair Encoding tokenizer for Hindi text, implemented using Streamlit.
|
| 14 |
+
|
| 15 |
+
## Features
|
| 16 |
+
- Tokenizes Hindi text using BPE algorithm
|
| 17 |
+
- Visualizes the tokenization process
|
| 18 |
|
| 19 |
## Dataset
|
| 20 |
|