Spaces:
Running
on
T4
Running
on
T4
Commit
•
15763b2
1
Parent(s):
8be8d39
Download tokenizer
Browse files
app.py
CHANGED
|
@@ -20,6 +20,8 @@ df = pd.read_csv(filename)
|
|
| 20 |
df.drop_duplicates(inplace=True)
|
| 21 |
print(f'Number of documents: {len(df)}')
|
| 22 |
|
|
|
|
|
|
|
| 23 |
corpus = []
|
| 24 |
sentence_count = []
|
| 25 |
for _, row in df.iterrows():
|
|
@@ -107,4 +109,4 @@ iface = gr.Interface(
|
|
| 107 |
],
|
| 108 |
allow_flagging=False
|
| 109 |
)
|
| 110 |
-
iface.launch()
|
|
|
|
| 20 |
df.drop_duplicates(inplace=True)
|
| 21 |
print(f'Number of documents: {len(df)}')
|
| 22 |
|
| 23 |
+
nltk.download('punkt')
|
| 24 |
+
|
| 25 |
corpus = []
|
| 26 |
sentence_count = []
|
| 27 |
for _, row in df.iterrows():
|
|
|
|
| 109 |
],
|
| 110 |
allow_flagging=False
|
| 111 |
)
|
| 112 |
+
iface.launch()
|