app.py

import gradio as gr

from transformers import AutoModel, pipeline, AutoTokenizer, AutoModelForSequenceClassification

access_token = "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"

model = AutoModelForSequenceClassification.from_pretrained("EkhiAzur/RoBERTA_3", token=access_token)

tokenizer = AutoTokenizer.from_pretrained(
  "EkhiAzur/RoBERTA_3",
  token = access_token,
  use_fast=True,
  add_prefix_space=True,
)

classifier = pipeline("text-classification", tokenizer=tokenizer, model=model, max_length=512,
                padding=True, truncation=True, batch_size=1)

def prozesatu(Testua, request: gr.Request):
    return str(request.headers["accept-language"])
    prediction = prozesatu.classifier(Testua)[0]
    if prediction["label"]=="GAI":
        return {"Gai":prediction["score"], "Ez gai": 1-prediction["score"]}
    else:
        return {"Gai":1-prediction["score"], "Ez gai": prediction["score"]}
    #return 'C1:{}. Probabilitatea:{:.2f}'.format(prediction["label"], round(prediction["score"], 2))

prozesatu.classifier = classifier

demo = gr.Interface(
    fn=prozesatu, 
    inputs=gr.Textbox(label="Testua", placeholder="Idatzi hemen testua..."), 
    outputs="label", 
    #interpretation="default",
    #examples=[["Gaur egungo teknologiak bikainak dira..."]]
    ).launch()

#gr.Interface(fn=prozesatu, inputs="text", outputs="text").launch()