app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

MODEL_NAME = "ayymen/NLLB-200-600M-Tamazight-All-Data"
LANGS = ["tzm_Tfng", "kab_Latn", "taq_Tfng", "taq_Latn","eng_Latn", "cat_Latn", "spa_Latn", "fra_Latn", "ary_Arab"]

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME).to(device)

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)


def translate(text, source_lang, target_lang, max_length=238):
    """
    Translate text from source language to target language
    """
    # src_lang = choose_language(source_lang)
    # tgt_lang= choose_language(target_lang)
    # if src_lang==None:
    #     return "Error: the source langage is incorrect"
    # elif tgt_lang==None:
    #     return "Error: the target language is incorrect"
    print(text)

    tokenizer.src_lang = source_lang

    inputs = tokenizer(text, return_tensors="pt").to(model.device)
    translated_tokens = model.generate(
            **inputs, forced_bos_token_id=tokenizer.convert_tokens_to_ids(target_lang)
            )
    translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]

    return translation


gradio_ui= gr.Interface(
    fn=translate,
    title="NLLB Tamazight Translation Demo",
    inputs= [
        gr.components.Textbox(label="Text"),
        gr.components.Dropdown(label="Source Language", choices=LANGS),
        gr.components.Dropdown(label="Target Language", choices=LANGS),
      #  gr.components.Slider(8, 400, value=400, step=8, label="Max Length")
    ],
    outputs=gr.components.Textbox(label="Translated text")
)

gradio_ui.launch()