Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -22,28 +22,37 @@ t2t_example = [["Paraphrase: Bu üründen çok memnun kaldım."]]
|
|
22 |
nli_example = [["Bunu çok beğendim. Bunu çok sevdim."]]
|
23 |
|
24 |
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
ttc = pipeline(model="boun-tabi-LMG/turna_classification_ttc4900", device=0)
|
29 |
# examples =long_text, title="Text Categorization")
|
30 |
-
product_reviews = pipeline(model="boun-tabi-LMG/turna_classification_tr_product_reviews", device=0)
|
31 |
-
#
|
32 |
-
title_gen = pipeline(model="boun-tabi-LMG/turna_title_generation_mlsum", device=0)
|
33 |
-
# examples =long_text, title="Title Generation", description="Enter a text to generate title to.")
|
34 |
-
sentiment_model = pipeline(model="boun-tabi-LMG/turna_classification_17bintweet_sentiment", device=0)
|
35 |
-
#examples=sentiment_example, title="Sentiment Analysis", description="Enter a text to generate title to.")
|
36 |
|
37 |
|
38 |
-
|
|
|
|
|
|
|
39 |
|
40 |
-
|
|
|
|
|
|
|
41 |
|
|
|
|
|
|
|
|
|
42 |
|
|
|
|
|
|
|
|
|
43 |
|
44 |
@spaces.GPU
|
45 |
-
def sentiment_analysis(input,
|
46 |
-
|
|
|
|
|
47 |
return sentiment_model(input)
|
48 |
else:
|
49 |
return product_reviews(input)
|
|
|
22 |
nli_example = [["Bunu çok beğendim. Bunu çok sevdim."]]
|
23 |
|
24 |
|
25 |
+
#ttc = pipeline(model="boun-tabi-LMG/turna_classification_ttc4900", device=0)
|
|
|
|
|
|
|
26 |
# examples =long_text, title="Text Categorization")
|
27 |
+
#product_reviews = pipeline(model="boun-tabi-LMG/turna_classification_tr_product_reviews", device=0)
|
28 |
+
#title_gen = pipeline(model="boun-tabi-LMG/turna_title_generation_mlsum", device=0)
|
|
|
|
|
|
|
|
|
29 |
|
30 |
|
31 |
+
@spaces.GPU
|
32 |
+
def nli(input, model_choice="turna_nli_nli_tr"):
|
33 |
+
nli_model = pipeline(model="boun-tabi-LMG/turna_nli_nli_tr", device=0)
|
34 |
+
stsb_model = pipeline(model="boun-tabi-LMG/turna_semantic_similarity_stsb_tr", device=0)
|
35 |
|
36 |
+
if model_choice=="turna_nli_nli_tr":
|
37 |
+
return nli_model(input)
|
38 |
+
else:
|
39 |
+
return stsb_model(input)
|
40 |
|
41 |
+
@spaces.GPU
|
42 |
+
def nli(input, model_choice="turna_nli_nli_tr"):
|
43 |
+
nli_model = pipeline(model="boun-tabi-LMG/turna_nli_nli_tr", device=0)
|
44 |
+
stsb_model = pipeline(model="boun-tabi-LMG/turna_semantic_similarity_stsb_tr", device=0)
|
45 |
|
46 |
+
if model_choice=="turna_nli_nli_tr":
|
47 |
+
return nli_model(input)
|
48 |
+
else:
|
49 |
+
return stsb_model(input)
|
50 |
|
51 |
@spaces.GPU
|
52 |
+
def sentiment_analysis(input, model_choice="turna_classification_17bintweet_sentiment"):
|
53 |
+
product_reviews = pipeline(model="boun-tabi-LMG/turna_classification_tr_product_reviews", device=0)
|
54 |
+
sentiment_model = pipeline(model="boun-tabi-LMG/turna_classification_17bintweet_sentiment", device=0)
|
55 |
+
if model_choice=="turna_classification_17bintweet_sentiment":
|
56 |
return sentiment_model(input)
|
57 |
else:
|
58 |
return product_reviews(input)
|