Spaces:
Running
Running
eljanmahammadli
commited on
Commit
•
2d19a26
1
Parent(s):
4302b12
Update app.py
Browse files
app.py
CHANGED
@@ -188,7 +188,7 @@ text_bc_model_path = "polygraf-ai/v3-bert-3-2m-trun-bc-lighter-spec"
|
|
188 |
text_bc_tokenizer = AutoTokenizer.from_pretrained(text_bc_model_path)
|
189 |
text_bc_model = AutoModelForSequenceClassification.from_pretrained(text_bc_model_path).to(device)
|
190 |
|
191 |
-
text_mc_model_path = "polygraf-ai/
|
192 |
text_mc_tokenizer = AutoTokenizer.from_pretrained(text_mc_model_path)
|
193 |
text_mc_model = AutoModelForSequenceClassification.from_pretrained(text_mc_model_path).to(device)
|
194 |
|
@@ -213,7 +213,7 @@ def update_character_count(text):
|
|
213 |
return f"{len(text)} characters"
|
214 |
|
215 |
|
216 |
-
def split_text_allow_complete_sentences_nltk(text, max_length=256, tolerance=40, min_last_segment_length=150, type_det
|
217 |
sentences = nltk.sent_tokenize(text)
|
218 |
segments = []
|
219 |
current_segment = []
|
|
|
188 |
text_bc_tokenizer = AutoTokenizer.from_pretrained(text_bc_model_path)
|
189 |
text_bc_model = AutoModelForSequenceClassification.from_pretrained(text_bc_model_path).to(device)
|
190 |
|
191 |
+
text_mc_model_path = "polygraf-ai/text-detect-mc-bert-base-uncased-mistral-openai-447k-256"
|
192 |
text_mc_tokenizer = AutoTokenizer.from_pretrained(text_mc_model_path)
|
193 |
text_mc_model = AutoModelForSequenceClassification.from_pretrained(text_mc_model_path).to(device)
|
194 |
|
|
|
213 |
return f"{len(text)} characters"
|
214 |
|
215 |
|
216 |
+
def split_text_allow_complete_sentences_nltk(text, max_length=256, tolerance=40, min_last_segment_length=150, type_det='bc'):
|
217 |
sentences = nltk.sent_tokenize(text)
|
218 |
segments = []
|
219 |
current_segment = []
|