Update app.py

app.py

@@ -1,48 +1,45 @@
 import gradio as gr
-import torch
-from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
+from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
 
-# Load Whisper for transcription
+# Load Whisper for ASR
 asr_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")
 
-# Load grammar scoring model
+# Load Grammar Scoring Model (CoLA)
 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
+# Load Grammar Correction Model (T5)
 correction_pipeline = pipeline("text2text-generation", model="vennify/t5-base-grammar-correction")
 
-def process_audio(audio_path):
-    # Transcribe
-    transcription = asr_pipeline(audio_path)["text"]
+def process_audio(audio):
+    if audio is None:
+        return "No audio provided.", "", ""
 
-    # Score grammar
-    grammar_result = grammar_pipeline(transcription)[0]
-    score_label = grammar_result["label"]
-    score_confidence = grammar_result["score"]
+    # Step 1: Transcription
+    transcription = asr_pipeline(audio)["text"]
 
-    # Suggest correction
-    corrected_text = correction_pipeline(transcription, max_length=128)[0]["generated_text"]
+    # Step 2: Grammar Scoring
+    score_output = grammar_pipeline(transcription)[0]
+    label = score_output["label"]
+    confidence = score_output["score"]
 
-    return transcription, f"{score_label} ({score_confidence:.2f})", corrected_text
+    # Step 3: Grammar Correction
+    corrected = correction_pipeline(transcription, max_length=128)[0]["generated_text"]
 
-# Gradio Interface
-interface = gr.Interface(
+    return transcription, f"{label} ({confidence:.2f})", corrected
+
+demo = gr.Interface(
     fn=process_audio,
-    inputs=gr.Audio(
-        source="microphone",  # enables both mic recording and upload
-        type="filepath",
-        label="🎤 Record or Upload Audio (.wav)"
-    ),
+    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath", label="🎤 Speak or Upload Audio (.wav)"),
     outputs=[
         gr.Textbox(label="📝 Transcription"),
         gr.Textbox(label="✅ Grammar Score"),
-        gr.Textbox(label="✍️ Suggested Correction")
+        gr.Textbox(label="✍️ Grammar Correction")
     ],
     title="🎙️ Voice Grammar Scorer",
-    description="Record or upload your voice (.wav). This app transcribes it, scores grammar, and suggests corrections."
+    description="Record or upload a WAV file. This app transcribes your voice, scores its grammar, and suggests corrections.",
 )
 
 if __name__ == "__main__":
-    interface.launch()
+    demo.launch()