app.py

import gradio as gr
import torch
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
import tempfile
import torchaudio

# Load Whisper for transcription
asr_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")

# Load grammar scoring model
cola_model = AutoModelForSequenceClassification.from_pretrained("textattack/roberta-base-CoLA")
cola_tokenizer = AutoTokenizer.from_pretrained("textattack/roberta-base-CoLA")
grammar_pipeline = pipeline("text-classification", model=cola_model, tokenizer=cola_tokenizer)

# Load grammar correction model
correction_pipeline = pipeline("text2text-generation", model="vennify/t5-base-grammar-correction")

def process_audio(audio_file):
    # Save uploaded file to temporary path
    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
        tmp.write(audio_file.read())
        tmp_path = tmp.name

    # Transcription
    transcription = asr_pipeline(tmp_path)["text"]

    # Grammar Scoring
    grammar_result = grammar_pipeline(transcription)[0]
    score_label = grammar_result["label"]
    score_confidence = grammar_result["score"]

    # Correction
    corrected_text = correction_pipeline(transcription, max_length=128)[0]["generated_text"]

    return transcription, f"{score_label} ({score_confidence:.2f})", corrected_text

# Gradio Interface
interface = gr.Interface(
    fn=process_audio,
    inputs=gr.Audio(type="file", label="Upload your .wav file"),
    outputs=[
        gr.Textbox(label="Transcription"),
        gr.Textbox(label="Grammar Score"),
        gr.Textbox(label="Grammar Correction")
    ],
    title="🎙️ Voice Grammar Scorer",
    description="Upload your voice (WAV file). This app transcribes it, scores grammar, and suggests corrections."
)

if __name__ == "__main__":
    interface.launch()