app.py

import gradio as gr
import torch
import numpy as np
from transformers import AutoModelForAudioClassification, AutoFeatureExtractor

MODEL_NAME = "your-username/your-model"

model = AutoModelForAudioClassification.from_pretrained(MODEL_NAME)
feature_extractor = AutoFeatureExtractor.from_pretrained(MODEL_NAME)

def predict(audio):
    waveform, sample_rate = audio
    
    inputs = feature_extractor(
        waveform,
        sampling_rate=sample_rate,
        return_tensors="pt"
    )
    
    with torch.no_grad():
        outputs = model(**inputs)
    
    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
    predicted_class = torch.argmax(probs, dim=-1).item()
    
    return f"Predicted Emotion: {model.config.id2label[predicted_class]}"

interface = gr.Interface(
    fn=predict,
    inputs=gr.Audio(type="numpy"),
    outputs="text",
    title="🎤 Voice Emotion Classifier",
    description="Upload an audio file to detect emotion"
)

interface.launch()