Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -6,12 +6,12 @@ from transformers import pipeline
|
|
| 6 |
import PyPDF2
|
| 7 |
import gradio as gr
|
| 8 |
|
| 9 |
-
#
|
| 10 |
spacy.cli.download("en_core_web_sm")
|
| 11 |
nlp = spacy.load("en_core_web_sm")
|
| 12 |
nltk.download('punkt')
|
| 13 |
|
| 14 |
-
#
|
| 15 |
device = 0 if torch.cuda.is_available() else -1
|
| 16 |
analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english", device=device)
|
| 17 |
|
|
@@ -47,6 +47,8 @@ def extract_pdf_text(file_path):
|
|
| 47 |
|
| 48 |
def analyze_and_complete(file_paths):
|
| 49 |
results = []
|
|
|
|
|
|
|
| 50 |
for file_path in file_paths:
|
| 51 |
if file_path.endswith(".pdf"):
|
| 52 |
text = extract_pdf_text(file_path)
|
|
@@ -54,7 +56,6 @@ def analyze_and_complete(file_paths):
|
|
| 54 |
with open(file_path, "r", encoding="utf-8") as file:
|
| 55 |
text = file.read()
|
| 56 |
|
| 57 |
-
output_directory = "/Users/Home/Library/Mobile Documents/com~apple~CloudDocs/osa/سيناريوهات/ليالي ألف ليلة"
|
| 58 |
filename_prefix = os.path.splitext(os.path.basename(file_path))[0]
|
| 59 |
|
| 60 |
spacy_entities = spacy_ner_analysis(text)
|
|
@@ -62,14 +63,28 @@ def analyze_and_complete(file_paths):
|
|
| 62 |
quotes = nltk_extract_quotes(text)
|
| 63 |
token_count = count_tokens(text)
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
results.append((str(spacy_entities), "\n".join(sentences), "\n".join(quotes), str(token_count)))
|
|
|
|
| 66 |
return results
|
| 67 |
|
| 68 |
-
#
|
| 69 |
interface = gr.Interface(
|
| 70 |
fn=analyze_and_complete,
|
| 71 |
inputs=gr.File(file_count="multiple", type="filepath"),
|
| 72 |
-
outputs=
|
| 73 |
title="Movie Script Analyzer and Completer",
|
| 74 |
description="Upload text, PDF, or DOCX files to analyze and complete the movie script."
|
| 75 |
)
|
|
|
|
| 6 |
import PyPDF2
|
| 7 |
import gradio as gr
|
| 8 |
|
| 9 |
+
# تحميل وتفعيل الأدوات المطلوبة
|
| 10 |
spacy.cli.download("en_core_web_sm")
|
| 11 |
nlp = spacy.load("en_core_web_sm")
|
| 12 |
nltk.download('punkt')
|
| 13 |
|
| 14 |
+
# التحقق من توفر GPU واستخدامه
|
| 15 |
device = 0 if torch.cuda.is_available() else -1
|
| 16 |
analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english", device=device)
|
| 17 |
|
|
|
|
| 47 |
|
| 48 |
def analyze_and_complete(file_paths):
|
| 49 |
results = []
|
| 50 |
+
output_directory = "/Volumes/CLOCKWORK T/clockworkspace/first pro"
|
| 51 |
+
|
| 52 |
for file_path in file_paths:
|
| 53 |
if file_path.endswith(".pdf"):
|
| 54 |
text = extract_pdf_text(file_path)
|
|
|
|
| 56 |
with open(file_path, "r", encoding="utf-8") as file:
|
| 57 |
text = file.read()
|
| 58 |
|
|
|
|
| 59 |
filename_prefix = os.path.splitext(os.path.basename(file_path))[0]
|
| 60 |
|
| 61 |
spacy_entities = spacy_ner_analysis(text)
|
|
|
|
| 63 |
quotes = nltk_extract_quotes(text)
|
| 64 |
token_count = count_tokens(text)
|
| 65 |
|
| 66 |
+
# حفظ النتائج إلى ملفات
|
| 67 |
+
with open(os.path.join(output_directory, f"{filename_prefix}_spacy_entities.txt"), "w", encoding="utf-8") as file:
|
| 68 |
+
file.write(str(spacy_entities))
|
| 69 |
+
|
| 70 |
+
with open(os.path.join(output_directory, f"{filename_prefix}_sentences.txt"), "w", encoding="utf-8") as file:
|
| 71 |
+
file.write("\n".join(sentences))
|
| 72 |
+
|
| 73 |
+
with open(os.path.join(output_directory, f"{filename_prefix}_quotes.txt"), "w", encoding="utf-8") as file:
|
| 74 |
+
file.write("\n".join(quotes))
|
| 75 |
+
|
| 76 |
+
with open(os.path.join(output_directory, f"{filename_prefix}_token_count.txt"), "w", encoding="utf-8") as file:
|
| 77 |
+
file.write(str(token_count))
|
| 78 |
+
|
| 79 |
results.append((str(spacy_entities), "\n".join(sentences), "\n".join(quotes), str(token_count)))
|
| 80 |
+
|
| 81 |
return results
|
| 82 |
|
| 83 |
+
# تعريف واجهة Gradio
|
| 84 |
interface = gr.Interface(
|
| 85 |
fn=analyze_and_complete,
|
| 86 |
inputs=gr.File(file_count="multiple", type="filepath"),
|
| 87 |
+
outputs=gr.outputs.JSON(),
|
| 88 |
title="Movie Script Analyzer and Completer",
|
| 89 |
description="Upload text, PDF, or DOCX files to analyze and complete the movie script."
|
| 90 |
)
|