File size: 1,182 Bytes
7d2250e
 
 
 
 
 
 
 
 
 
 
 
a0783ba
4fc24ec
 
743d68a
4fc24ec
 
 
 
 
ac4ddfc
7d2250e
 
 
 
6fd2f10
743d68a
7d2250e
 
f6ac75e
7d2250e
 
 
 
743d68a
f6ac75e
 
743d68a
356f076
7d2250e
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
import gradio as gr
import nagisa


def tokenize(text):
    tokens = nagisa.tagging(text)
    return tokens.words, tokens.postags


num_input_lines = 3
input_placeholder = "Please input text here."
title = "Japanese tokenization demo"
default_text = "ここにテキストを入力し、Enter を押してください。"
description = """
This is a demo page for nagisa's tokenization.
Nagisa is a Python module used for tokenizing and performing Part-of-Speech (POS) tagging on Japanese text.
It is designed to be a simple and easy-to-use tool.
To try it out, enter some text in the box  below and press submit.
https://github.com/taishi-i/nagisa
"""


examples = ["Pythonで簡単に使えるツールです", "3月に見た「3月のライオン」", "福岡・博多の観光情報"]

iface = gr.Interface(
    fn=tokenize,
    inputs=gr.Textbox(
        label="Input text",
        lines=num_input_lines,
        placeholder=input_placeholder,
        value=default_text,
    ),
    title=title,
    description=description,
    examples=examples,
    outputs=[
        gr.Textbox(label="Words"),
        gr.Textbox(label="POS tags"),
    ],
    live=True,
)


iface.launch()