app.py

import gradio as gr
from transformers import AutoTokenizer, pipeline
from optimum.onnxruntime import ORTModelForSequenceClassification

model_id = "SamLowe/roberta-base-go_emotions-onnx"
file_name = "onnx/model_quantized.onnx"

model = ORTModelForSequenceClassification.from_pretrained(model_id, file_name=file_name)
tokenizer = AutoTokenizer.from_pretrained(model_id)

classifier = pipeline(
    task = "text-classification",
    model = model,
    tokenizer = tokenizer,
    top_k = None,
    function_to_apply = "sigmoid",
)

def predict(param_0):
    results = classifier(param_0)
    return {
        "label": results[0][0]["label"],
        "confidences": results[0]
    }

demo = gr.Interface(
    fn = predict,
    inputs = 'text',
    outputs = 'json',
)

demo.launch()