Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -9,11 +9,9 @@ import io
|
|
| 9 |
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
|
| 10 |
|
| 11 |
# Function to extract text from different file types
|
| 12 |
-
def extract_text(
|
| 13 |
try:
|
| 14 |
-
#
|
| 15 |
-
file_bytes = file_obj.read()
|
| 16 |
-
file_obj.seek(0)
|
| 17 |
header = file_bytes[:4]
|
| 18 |
|
| 19 |
# Determine file type based on magic numbers
|
|
@@ -40,8 +38,8 @@ def extract_text(file_obj):
|
|
| 40 |
return f"❌ Error reading file: {str(e)}"
|
| 41 |
|
| 42 |
# Summarize the extracted text
|
| 43 |
-
def summarize_file(
|
| 44 |
-
text = extract_text(
|
| 45 |
if not text or len(text.strip()) == 0:
|
| 46 |
return "❌ No text found in the uploaded file."
|
| 47 |
|
|
@@ -62,7 +60,5 @@ demo = gr.Interface(
|
|
| 62 |
demo.launch()
|
| 63 |
|
| 64 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
|
| 68 |
|
|
|
|
| 9 |
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
|
| 10 |
|
| 11 |
# Function to extract text from different file types
|
| 12 |
+
def extract_text(file_bytes):
|
| 13 |
try:
|
| 14 |
+
# file_bytes is already a bytes object
|
|
|
|
|
|
|
| 15 |
header = file_bytes[:4]
|
| 16 |
|
| 17 |
# Determine file type based on magic numbers
|
|
|
|
| 38 |
return f"❌ Error reading file: {str(e)}"
|
| 39 |
|
| 40 |
# Summarize the extracted text
|
| 41 |
+
def summarize_file(file_bytes):
|
| 42 |
+
text = extract_text(file_bytes)
|
| 43 |
if not text or len(text.strip()) == 0:
|
| 44 |
return "❌ No text found in the uploaded file."
|
| 45 |
|
|
|
|
| 60 |
demo.launch()
|
| 61 |
|
| 62 |
|
|
|
|
|
|
|
| 63 |
|
| 64 |
|