app.py

import gradio as gr

from transformers import M2M100ForConditionalGeneration
from tokenization_small100 import SMALL100Tokenizer

langs = """Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Breton (br), Bosnian (bs), Catalan; Valencian (ca), Cebuano (ceb), Czech (cs), Welsh (cy), Danish (da), German (de), Greeek (el), English (en), Spanish (es), Estonian (et), Persian (fa), Fulah (ff), Finnish (fi), French (fr), Western Frisian (fy), Irish (ga), Gaelic; Scottish Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Croatian (hr), Haitian; Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Igbo (ig), Iloko (ilo), Icelandic (is), Italian (it), Japanese (ja), Javanese (jv), Georgian (ka), Kazakh (kk), Central Khmer (km), Kannada (kn), 
Korean (ko), Luxembourgish; Letzeburgesch (lb), Ganda (lg), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Burmese (my), Nepali (ne), Dutch; Flemish (nl), Norwegian (no), Northern Sotho (ns), Occitan (post 1500) (oc), Oriya (or), Panjabi; Punjabi (pa), Polish (pl), Pushto; Pashto (ps), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Russian (ru), Sindhi (sd), Sinhala; Sinhalese (si), Slovak (sk), 
Slovenian (sl), Somali (so), Albanian (sq), Serbian (sr), Swati (ss), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Thai (th), Tagalog (tl), Tswana (tn), 
Turkish (tr), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Wolof (wo), Xhosa (xh), Yiddish (yi), Yoruba (yo), Chinese (zh), Zulu (zu)"""
lang_list = [lang.strip().split(" ")[-1][1:-1] for lang in langs.split(',')]

model = M2M100ForConditionalGeneration.from_pretrained("alirezamsh/small100")
tokenizer = SMALL100Tokenizer.from_pretrained("alirezamsh/small100")

def translate(lang, text):
    tokenizer.tgt_lang = lang
    encoded_text = tokenizer(text, return_tensors="pt")
    generated_tokens = model.generate(**encoded_text)
    return tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]

with gr.Blocks(analytics_enabled=False) as app:
    
    Source = gr.Textbox( label="Source" )
    Language = gr.Dropdown( lang_list, label="Language" )
    Translate = gr.Button( "Translate" )
    Result = gr.Textbox( label="Result" )

    Translate.click(
        translate,
        inputs=[ Source, Language ],
        outputs=[Result],
        api_name="translate",
    )

    app.launch( enable_queue=True, inline=True )
    block.queue( concurrency_count=2 )