Spaces:
Sleeping
Sleeping
Commit
·
812bb26
1
Parent(s):
1287e6c
Adding token length
Browse files
app.py
CHANGED
@@ -8,7 +8,7 @@ tokenizer.load('models/english_5000.model')
|
|
8 |
def inference(input_text):
|
9 |
tokens = tokenizer.encode_ordinary(input_text)
|
10 |
|
11 |
-
return tokens
|
12 |
|
13 |
title = "A bilingual tokenizer build using opus and wikipedia data"
|
14 |
description = "A simple Gradio interface to see tokenization of Hindi and English(Hinglish) text"
|
@@ -22,6 +22,7 @@ demo = gr.Interface(
|
|
22 |
gr.Textbox(label="Enter any sentence in Hindi, English or both language", type="text"),
|
23 |
],
|
24 |
outputs = [
|
|
|
25 |
gr.Textbox(label="Output", type="text")
|
26 |
],
|
27 |
title = title,
|
|
|
8 |
def inference(input_text):
|
9 |
tokens = tokenizer.encode_ordinary(input_text)
|
10 |
|
11 |
+
return len(tokens), tokens
|
12 |
|
13 |
title = "A bilingual tokenizer build using opus and wikipedia data"
|
14 |
description = "A simple Gradio interface to see tokenization of Hindi and English(Hinglish) text"
|
|
|
22 |
gr.Textbox(label="Enter any sentence in Hindi, English or both language", type="text"),
|
23 |
],
|
24 |
outputs = [
|
25 |
+
gr.Label(label="Token count"),
|
26 |
gr.Textbox(label="Output", type="text")
|
27 |
],
|
28 |
title = title,
|