Spaces:
Sleeping
Sleeping
no message
Browse files
main.py
CHANGED
@@ -99,11 +99,15 @@ def split_text_by_tokens(text, max_tokens=1024):
|
|
99 |
def summarize_large_text(text):
|
100 |
chunks, token_counts = split_text_by_tokens(text, max_tokens=1024 - 10) # Slight buffer to avoid edge cases
|
101 |
summaries = []
|
|
|
|
|
102 |
for chunk in chunks:
|
|
|
103 |
# Perform summarization on the chunk
|
104 |
summary = summarizer(chunk, max_length=500, min_length=100, do_sample=False)
|
105 |
if summary:
|
106 |
summaries.append(summary[0]['summary_text'])
|
|
|
107 |
combined_summary = ' '.join(summaries)
|
108 |
return combined_summary
|
109 |
|
|
|
99 |
def summarize_large_text(text):
|
100 |
chunks, token_counts = split_text_by_tokens(text, max_tokens=1024 - 10) # Slight buffer to avoid edge cases
|
101 |
summaries = []
|
102 |
+
print("Starting summarization of chunks...")
|
103 |
+
|
104 |
for chunk in chunks:
|
105 |
+
print(f"Summarizing chunk: {chunk[:50]}...") # Print the first 50 characters of the chunk
|
106 |
# Perform summarization on the chunk
|
107 |
summary = summarizer(chunk, max_length=500, min_length=100, do_sample=False)
|
108 |
if summary:
|
109 |
summaries.append(summary[0]['summary_text'])
|
110 |
+
print(f"Summary: {summary[0]['summary_text'][:50]}") # Print the first 50 characters of the summary
|
111 |
combined_summary = ' '.join(summaries)
|
112 |
return combined_summary
|
113 |
|