add app.py and requirements.txt
Browse files- app.py +87 -0
- requirements.txt +8 -0
app.py
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from toiro import tokenizers
|
3 |
+
|
4 |
+
num_input_lines = 3
|
5 |
+
default_text = "γγγ«γγγΉγγε
₯εγγSubmit γζΌγγ¦γγ γγγ"
|
6 |
+
title = "Japanese Tokenizer Comparison"
|
7 |
+
description = """
|
8 |
+
This is a demo comparing Japanese tokenizers. You can compare the tokenization results of tools that are available with just a `pip install` in Python.
|
9 |
+
"""
|
10 |
+
|
11 |
+
article = """
|
12 |
+
|
13 |
+
# How to install each library
|
14 |
+
|
15 |
+
[Janome](https://github.com/mocobeta/janome):
|
16 |
+
```
|
17 |
+
pip install janome
|
18 |
+
```
|
19 |
+
|
20 |
+
[nagisa](https://github.com/taishi-i/nagisa):
|
21 |
+
```
|
22 |
+
pip install nagisa
|
23 |
+
```
|
24 |
+
|
25 |
+
[sudachi.rs](https://github.com/WorksApplications/sudachi.rs):
|
26 |
+
```
|
27 |
+
pip install sudachipy sudachidict_core
|
28 |
+
```
|
29 |
+
|
30 |
+
[mecab-python3](https://github.com/SamuraiT/mecab-python3):
|
31 |
+
```
|
32 |
+
pip install mecab-python3
|
33 |
+
```
|
34 |
+
|
35 |
+
[fugashi_ipadic](https://github.com/polm/fugashi):
|
36 |
+
```
|
37 |
+
pip install fugashi ipadic
|
38 |
+
```
|
39 |
+
|
40 |
+
[fugashi_ipadic](https://github.com/polm/fugashi):
|
41 |
+
```
|
42 |
+
pip install fugashi unidic-lite
|
43 |
+
```
|
44 |
+
|
45 |
+
"""
|
46 |
+
|
47 |
+
|
48 |
+
def tokenize(text):
|
49 |
+
words_janome = tokenizers.tokenize_janome(text)
|
50 |
+
words_nagisa = tokenizers.tokenize_nagisa(text)
|
51 |
+
words_sudachirs = tokenizers.tokenize_sudachipy(text)
|
52 |
+
words_mecabpython3 = tokenizers.tokenize_mecab(text)
|
53 |
+
words_fugashi_ipadic = tokenizers.tokenize_fugashi_ipadic(text)
|
54 |
+
words_fugashi_unidic = tokenizers.tokenize_fugashi_unidic(text)
|
55 |
+
|
56 |
+
return (
|
57 |
+
words_janome,
|
58 |
+
words_nagisa,
|
59 |
+
words_sudachirs,
|
60 |
+
words_mecabpython3,
|
61 |
+
words_fugashi_ipadic,
|
62 |
+
words_fugashi_unidic,
|
63 |
+
)
|
64 |
+
|
65 |
+
|
66 |
+
iface = gr.Interface(
|
67 |
+
fn=tokenize,
|
68 |
+
inputs=gr.inputs.Textbox(
|
69 |
+
label="Input text",
|
70 |
+
lines=num_input_lines,
|
71 |
+
default=default_text,
|
72 |
+
),
|
73 |
+
title=title,
|
74 |
+
description=description,
|
75 |
+
article=article,
|
76 |
+
outputs=[
|
77 |
+
gr.outputs.Textbox(label="Janome"),
|
78 |
+
gr.outputs.Textbox(label="nagisa"),
|
79 |
+
gr.outputs.Textbox(label="sudachi.rs"),
|
80 |
+
gr.outputs.Textbox(label="mecab-python3"),
|
81 |
+
gr.outputs.Textbox(label="fugashi_ipadic"),
|
82 |
+
gr.outputs.Textbox(label="fugashi_unidic"),
|
83 |
+
],
|
84 |
+
)
|
85 |
+
|
86 |
+
|
87 |
+
iface.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
toiro
|
2 |
+
nagisa
|
3 |
+
sudachipy
|
4 |
+
sudachidict_core
|
5 |
+
mecab-python3
|
6 |
+
fugashi
|
7 |
+
ipadic
|
8 |
+
unidic-lite
|