app.py

import gradio as gr
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer

model_name = "dsfsi/nso-en-m2m100-gov"
tokenizer = M2M100Tokenizer.from_pretrained(model_name)
model = M2M100ForConditionalGeneration.from_pretrained(model_name)

print(tokenizer.lang_code_to_token)

tokenizer.src_lang = "ns"
model.config.forced_bos_token_id = tokenizer.get_lang_id("en")

def translate(inp):
    inputs = tokenizer(inp, return_tensors="pt")
    translated_tokens = model.generate(**inputs, max_length=512, forced_bos_token_id=tokenizer.get_lang_id("en"))
    translated_text = tokenizer.decode(translated_tokens[0], skip_special_tokens=True)
    return translated_text


logo = """
<div style='text-align: center;'>
    <img src='file/logo_transparent_small.png' alt='Logo' width='150'/>
</div>
"""

description = """
<p style='text-align: center;'>
    Northern Sotho to English Translation
</p>
<p>
    This space provides a translation service from Northern Sotho to English using the M2M100 model, fine-tuned for low-resource languages. It supports researchers, linguists, and users working with Northern Sotho texts.
</p>
"""

article = """
<div style='text-align: center;'>
    <a href='https://github.com/dsfsi/nso-en-m2m100-gov' target='_blank'>GitHub</a> |
    <a href='https://docs.google.com/forms/d/e/1FAIpQLSf7S36dyAUPx2egmXbFpnTBuzoRulhL5Elu-N1eoMhaO7v10w/viewform' target='_blank'>Feedback Form</a> |
    <a href='https://arxiv.org/abs/2303.03750' target='_blank'>Arxiv</a>
</div>
<br/>
"""

authors = """
<div style='text-align: center;'>
    Authors: Vukosi Marivate, Matimba Shingange, Richard Lastrucci, 
    Isheanesu Joseph Dzingirai, Jenalea Rajab
</div>
"""

citation = """
<pre style="text-align: left; white-space: pre-wrap;">
@inproceedings{lastrucci-etal-2023-preparing,
    title = "Preparing the Vuk{'}uzenzele and {ZA}-gov-multilingual {S}outh {A}frican multilingual corpora",
    author = "Richard Lastrucci and Isheanesu Dzingirai and Jenalea Rajab 
              and Andani Madodonga and Matimba Shingange and Daniel Njini and Vukosi Marivate",
    booktitle = "Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023)",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.rail-1.3",
    pages = "18--25"
}
</pre>
"""

doi = """
<div style='text-align: center;'>
    DOI: <a href="https://doi.org/10.48550/arXiv.2303.03750" target="_blank">10.48550/arXiv.2303.03750</a>
</div>
"""

with gr.Blocks() as demo:
    gr.Markdown(logo)   
    gr.Markdown(description)
    gr.Markdown(article)

    with gr.Interface(
        fn=translate,
        title="Northern Sotho to English Translation",
        description=description,
        article=article,
        inputs=gr.components.Textbox(lines=5, placeholder="Enter Northern Sotho text (maximum 5 lines)", label="Input"),
        outputs="text"
    ) as iface:
        iface.launch(enable_queue=True)

    with gr.Accordion("More Information", open=False):
        gr.Markdown("""
        <h4 style="text-align: center;">More information about the space</h4>
        <p>This is a variant of the M2M100 model, fine-tuned on a multilingual dataset 
        to support translation from Northern Sotho (Sepedi) to English. The model was trained 
        with a focus on improving translation accuracy for low-resource languages.</p>
        """)
        gr.Markdown(authors)
        gr.Markdown(citation)
        gr.Markdown(doi)

demo.launch(enable_queue=True)