Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -30,7 +30,10 @@ def utf8_tokens(tokens):
|
|
30 |
def tokenize_text(tokenizer_name_1, tokenizer_name_2, text, hf_token=None):
|
31 |
def tokenize_with_model(tokenizer_name):
|
32 |
try:
|
33 |
-
|
|
|
|
|
|
|
34 |
tokens = tokenizer.tokenize(text)
|
35 |
word_count = len(text.split())
|
36 |
token_count = len(tokens)
|
|
|
30 |
def tokenize_text(tokenizer_name_1, tokenizer_name_2, text, hf_token=None):
|
31 |
def tokenize_with_model(tokenizer_name):
|
32 |
try:
|
33 |
+
if hf_token:
|
34 |
+
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name, use_auth_token=hf_token)
|
35 |
+
else:
|
36 |
+
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
|
37 |
tokens = tokenizer.tokenize(text)
|
38 |
word_count = len(text.split())
|
39 |
token_count = len(tokens)
|