Checker / app.py
abischoff's picture
Update app.py
55ad0fe verified
Raw History Blame Contribute Delete
2.93 kB
import gradio as gr
import numpy as np
from transformers import Trainer, AutoTokenizer, XLMRobertaForSequenceClassification
import torch
import pickle
import re
import PyPDF2
import docx
import xml.etree.ElementTree as ET
def checker(content):
#if isinstance(content, bytes):#falls es ein Byte-String ist
# content = content.decode('utf-8')
sentences = re.split(r"(?<=[!.;?:])\s+(?![a-zà-öø-ÿα-ωа-яא-תء-ي])", content)
model_name = "abischoff/test-trainer"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = XLMRobertaForSequenceClassification.from_pretrained(model_name,num_labels=1)
sum = 0.0
bias = -0.0666
for dic in sentences:
inputs = tokenizer(dic.strip(), return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits.flatten()[0].numpy()+bias
logits = np.clip(logits,0,1)
sum += logits
res = sum / len(sentences)
return res
# Funktion zur Verarbeitung der hochgeladenen Datei
def process_file(file):
if file:
content = read_file(file)
if content == "":
return "Datei konnte nicht gelesen werden"
else:
res = checker(content)
return res
return "Fehler bei der Verarbeitung"
# lese die Datei ein
def read_file(file):
content = ""
if ".pdf" in file.name:
# creating a pdf reader object
reader = PyPDF2.PdfReader(file.name)
counter = 0
while counter < len(reader.pages):
content += reader.pages[counter].extract_text()
counter += 1
elif ".docx" in file.name:
doc = docx.Document(file.name)
for para in doc.paragraphs:
content += para.text
elif ".xml" in file.name:
tree = ET.parse(file.name)
root = tree.getroot()
for text in root.itertext():
if text != "":
content += text
else:
with open(file.name, 'r', encoding='utf-8') as f:
content = f.read()
#with open(file.name, 'rb') as f:
# content = pickle.load(f)
print(content)
return content
def is_valid_file(file_path: str, file_types: list[str]) -> bool:
file_extension = os.path.splitext(file_path)[1]
return file_extension in file_types
# Gradio Interface
with gr.Blocks(css=".gr-box {border-radius: 8px;}") as demo:
# App-Titel
gr.Markdown(
"""
## 📝 Checker
Ziehe deine Datei hierhin und lasse den Quality Score errechnen!
"""
)
# Drag & Drop Datei-Upload
with gr.Row():
with gr.Column():
file_input = gr.File(label="Datei hochladen", file_types=['file'], interactive=True)
with gr.Column():
output_text = gr.Textbox(label="Dateiinhalt", lines=10)
# Callback zum Verarbeiten der Datei
file_input.change(fn=process_file, inputs=[file_input], outputs=[output_text])
# App starten
demo.launch()