app.py

import gradio as gr
from transformers import pipeline
import torch

def create_analyzers():
    """Initialize speech and emotion analyzers"""
    try:
        # Use tiny whisper model for speed and reliability
        speech_recognizer = pipeline(
            "automatic-speech-recognition",
            model="openai/whisper-tiny.en",
            chunk_length_s=30
        )
        
        # Use smaller emotion classifier
        emotion_classifier = pipeline(
            "text-classification",
            model="SamLowe/roberta-base-go_emotions",
            top_k=1
        )
        
        return speech_recognizer, emotion_classifier
    except Exception as e:
        print(f"Model loading error: {e}")
        return None, None

def analyze_tone(audio_file):
    """Analyze the emotional tone of speech"""
    if audio_file is None:
        return "No input", "N/A"
    
    try:
        # Get models
        speech_recognizer, emotion_classifier = create_analyzers()
        
        # Transcribe audio
        transcription = speech_recognizer(audio_file)
        text = transcription["text"]
        
        if not text.strip():
            return "No speech detected", "N/A"
            
        print(f"Transcribed text: {text}")  # For debugging
        
        # Analyze emotion
        result = emotion_classifier(text)[0][0]
        emotion = result['label'].replace('_', ' ').title()
        confidence = f"{result['score']:.1%}"
        
        return emotion, confidence
        
    except Exception as e:
        print(f"Analysis error: {e}")
        return f"Error: {str(e)}", "N/A"

# Create minimal interface
interface = gr.Interface(
    fn=analyze_tone,
    inputs=[
        gr.Audio(
            sources=["microphone", "upload"],
            type="filepath",
            label="Audio Input"
        )
    ],
    outputs=[
        gr.Textbox(label="Emotion"),
        gr.Textbox(label="Confidence")
    ],
    title="Speech Emotion Analyzer",
    description="Record or upload audio to detect the emotional tone.",
)

if __name__ == "__main__":
    interface.launch(server_name="0.0.0.0", share=True)