app.py

import gradio as gr
import numpy as np
import torch
from transformers import pipeline
import librosa
import soundfile as sf

class EmotionRecognizer:
    def __init__(self):
        self.classifier = pipeline(
            "audio-classification",
            model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
            device=0 if torch.cuda.is_available() else -1
        )
        self.target_sr = 16000
        self.max_duration = 10

    def process_audio(self, audio_path):
        try:
            audio, orig_sr = sf.read(audio_path)
            if len(audio.shape) > 1:
                audio = np.mean(audio, axis=1)
                
            if orig_sr != self.target_sr:
                audio = librosa.resample(
                    y=audio.astype(np.float32),
                    orig_sr=orig_sr,
                    target_sr=self.target_sr
                )
            else:
                audio = audio.astype(np.float32)
            
            audio = librosa.util.normalize(audio)
            max_samples = self.max_duration * self.target_sr
            if len(audio) > max_samples:
                audio = audio[:max_samples]
            else:
                audio = np.pad(audio, (0, max(0, max_samples - len(audio))))
            
            results = self.classifier(
                {"array": audio, "sampling_rate": self.target_sr}
            )
            
            labels = [res["label"] for res in results]
            scores = [res["score"] * 100 for res in results]
            
            text_output = "\n".join([f"{label}: {score:.2f}%" for label, score in zip(labels, scores)])
            plot_data = {"labels": labels, "values": scores}
            
            return text_output, plot_data
            
        except Exception as e:
            return f"Error processing audio: {str(e)}", None

def create_interface():
    recognizer = EmotionRecognizer()
    
    with gr.Blocks(title="Audio Emotion Recognition") as interface:
        gr.Markdown("# 🎙️ Audio Emotion Recognition")
        gr.Markdown("Record or upload English speech (3-10 seconds)")
        
        with gr.Row():
            with gr.Column():
                audio_input = gr.Audio(
                    sources=["microphone", "upload"],
                    type="filepath",
                    label="Input Audio"
                )
                submit_btn = gr.Button("Analyze", variant="primary")
                
            with gr.Column():
                text_output = gr.Textbox(label="Results", interactive=False)
                plot_output = gr.BarPlot(
                    label="Confidence Scores",
                    x="labels",
                    y="values",
                    color="labels",
                    height=300
                )
        
        submit_btn.click(
            fn=recognizer.process_audio,
            inputs=audio_input,
            outputs=[text_output, plot_output]
        )
    
    return interface

if __name__ == "__main__":
    demo = create_interface()
    demo.launch()