Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -208,13 +208,8 @@ def classify_emotion(text, classifier):
|
|
208 |
all_scores = []
|
209 |
for chunk in chunks:
|
210 |
try:
|
211 |
-
|
212 |
-
|
213 |
-
truncation=True,
|
214 |
-
max_length=512,
|
215 |
-
return_tensors="pt"
|
216 |
-
)
|
217 |
-
result = classifier(chunk, truncation=True, max_length=512)
|
218 |
scores = result[0]
|
219 |
all_scores.append(scores)
|
220 |
except Exception as chunk_error:
|
@@ -226,11 +221,10 @@ def classify_emotion(text, classifier):
|
|
226 |
count = len(all_scores)
|
227 |
|
228 |
for scores in all_scores:
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
label_scores[label] += score['score']
|
234 |
|
235 |
avg_scores = {label: score/count for label, score in label_scores.items()}
|
236 |
final_emotion = max(avg_scores.items(), key=lambda x: x[1])[0]
|
@@ -241,7 +235,7 @@ def classify_emotion(text, classifier):
|
|
241 |
except Exception as e:
|
242 |
st.warning(f"Error in emotion classification: {str(e)}")
|
243 |
return "LABEL_2"
|
244 |
-
|
245 |
def get_embedding_for_text(text, tokenizer, model):
|
246 |
"""Get embedding for complete text."""
|
247 |
chunks = split_text(text)
|
|
|
208 |
all_scores = []
|
209 |
for chunk in chunks:
|
210 |
try:
|
211 |
+
# Direct classification without additional tokenization
|
212 |
+
result = classifier(chunk)
|
|
|
|
|
|
|
|
|
|
|
213 |
scores = result[0]
|
214 |
all_scores.append(scores)
|
215 |
except Exception as chunk_error:
|
|
|
221 |
count = len(all_scores)
|
222 |
|
223 |
for scores in all_scores:
|
224 |
+
label = scores['label']
|
225 |
+
if label not in label_scores:
|
226 |
+
label_scores[label] = 0
|
227 |
+
label_scores[label] += scores['score']
|
|
|
228 |
|
229 |
avg_scores = {label: score/count for label, score in label_scores.items()}
|
230 |
final_emotion = max(avg_scores.items(), key=lambda x: x[1])[0]
|
|
|
235 |
except Exception as e:
|
236 |
st.warning(f"Error in emotion classification: {str(e)}")
|
237 |
return "LABEL_2"
|
238 |
+
|
239 |
def get_embedding_for_text(text, tokenizer, model):
|
240 |
"""Get embedding for complete text."""
|
241 |
chunks = split_text(text)
|