File size: 2,278 Bytes
02ad7ce 8203218 02ad7ce a183e25 02ad7ce 8203218 02ad7ce |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
import fitz # PyMuPDF
import re
from datasets import Dataset
from transformers import AutoModelForCausalLM, TrainingArguments, Trainer
import gradio as gr
from transformers import pipeline
def extract_text_from_pdf(pdf_path):
"""Extract text from a PDF file"""
doc = fitz.open(pdf_path)
text = ""
for page in doc:
text += page.get_text("text") + "\n"
return text
pdf_text = extract_text_from_pdf("new-american-standard-bible.pdf")
#print(pdf_text[:1000]) # Preview first 1000 characters
def preprocess_text(text):
"""Clean and preprocess text"""
text = re.sub(r'\s+', ' ', text) # Remove extra whitespace
text = text.strip()
return text
clean_text = preprocess_text(pdf_text)
#print(clean_text[:1000]) # Preview cleaned text
# Create a dataset from text
data = {"text": [clean_text]} # Single text entry
dataset = Dataset.from_dict(data)
# Tokenize text
from transformers import AutoTokenizer
model_name = "distilbert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
def tokenize_function(examples):
tokens = tokenizer(examples["text"], truncation=True, padding="max_length", max_length=512)
tokens["labels"] = tokens["input_ids"].copy() # Use input as labels for unsupervised learning
return tokens
tokenized_datasets = dataset.map(tokenize_function, batched=True)
model = AutoModelForCausalLM.from_pretrained(model_name) # Adjust for task
training_args = TrainingArguments(
output_dir="./results",
evaluation_strategy="epoch",
learning_rate=2e-5,
per_device_train_batch_size=8,
per_device_eval_batch_size=8,
num_train_epochs=3,
weight_decay=0.01,
save_strategy="epoch",
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets,
eval_dataset=tokenized_datasets,
tokenizer=tokenizer,
)
trainer.train()
model.save_pretrained("./distilbert-base-uncased-fine_tuned_model-NASB")
tokenizer.save_pretrained("./distilbert-base-uncased-fine_tuned_model-NASB")
classifier = pipeline("text-classification", model="./distilbert-base-uncased-fine_tuned_model-NASB")
def chatbot_response(text):
return classifier(text)
iface = gr.Interface(fn=chatbot_response, inputs="text", outputs="text")
iface.launch() |