Spaces:
Running
Running
TeacherPuffy
commited on
Update app.py
Browse files
app.py
CHANGED
@@ -21,8 +21,16 @@ def call_api(prompt):
|
|
21 |
|
22 |
# Function to segment the text file into chunks of 3000 words
|
23 |
def segment_text(file_path):
|
24 |
-
|
25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
words = text.split()
|
27 |
chunks = [" ".join(words[i:i + 3000]) for i in range(0, len(words), 3000)]
|
28 |
return chunks
|
@@ -42,7 +50,7 @@ def process_text(file, prompt):
|
|
42 |
# Save results as individual text files
|
43 |
os.makedirs("outputs", exist_ok=True)
|
44 |
for idx, result in enumerate(results):
|
45 |
-
with open(f"outputs/output_{idx}.txt", "w") as f:
|
46 |
f.write(result)
|
47 |
|
48 |
# Upload to Hugging Face dataset
|
@@ -75,5 +83,5 @@ with gr.Blocks() as demo:
|
|
75 |
outputs=[output_zip, output_message]
|
76 |
)
|
77 |
|
78 |
-
# Launch the Gradio app
|
79 |
-
demo.launch()
|
|
|
21 |
|
22 |
# Function to segment the text file into chunks of 3000 words
|
23 |
def segment_text(file_path):
|
24 |
+
try:
|
25 |
+
# Try reading with UTF-8 encoding first
|
26 |
+
with open(file_path, "r", encoding="utf-8") as f:
|
27 |
+
text = f.read()
|
28 |
+
except UnicodeDecodeError:
|
29 |
+
# Fallback to latin-1 encoding if UTF-8 fails
|
30 |
+
with open(file_path, "r", encoding="latin-1") as f:
|
31 |
+
text = f.read()
|
32 |
+
|
33 |
+
# Split the text into chunks of 3000 words
|
34 |
words = text.split()
|
35 |
chunks = [" ".join(words[i:i + 3000]) for i in range(0, len(words), 3000)]
|
36 |
return chunks
|
|
|
50 |
# Save results as individual text files
|
51 |
os.makedirs("outputs", exist_ok=True)
|
52 |
for idx, result in enumerate(results):
|
53 |
+
with open(f"outputs/output_{idx}.txt", "w", encoding="utf-8") as f:
|
54 |
f.write(result)
|
55 |
|
56 |
# Upload to Hugging Face dataset
|
|
|
83 |
outputs=[output_zip, output_message]
|
84 |
)
|
85 |
|
86 |
+
# Launch the Gradio app with a public link
|
87 |
+
demo.launch(share=True)
|