Create app.py

app.py

@@ -0,0 +1,44 @@
+import streamlit as st
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline
+
+# Load grammar correction model
+model_name = "vennify/t5-base-grammar-correction"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+
+# Load explanation model
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+
+explain_model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
+explain_tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
+
+def correct_text(text):
+    input_text = "gec: " + text
+    result = pipe(input_text, max_length=512, clean_up_tokenization_spaces=True)
+    return result[0]['generated_text']
+
+def explain_corrections(original, corrected):
+    prompt = f"""Original: {original}
+Corrected: {corrected}
+Explain the changes made, identify grammar or spelling issues, and give writing improvement tips."""
+    inputs = explain_tokenizer(prompt, return_tensors="pt", truncation=True)
+    outputs = explain_model.generate(**inputs, max_length=512)
+    return explain_tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Streamlit UI
+st.title("✍️ English Writing Assistant")
+user_input = st.text_area("Enter your sentence, paragraph, or essay:")
+
+if st.button("Check & Improve"):
+    if user_input.strip() == "":
+        st.warning("Please enter some text.")
+    else:
+        corrected = correct_text(user_input)
+        explanation = explain_corrections(user_input, corrected)
+
+        st.subheader("✅ Corrected Text:")
+        st.write(corrected)
+
+        st.subheader("📘 Explanation & Suggestions:")
+        st.write(explanation)