| import gradio as gr | |
| from transformers import M2M100ForConditionalGeneration | |
| from tokenization_small100 import SMALL100Tokenizer | |
| langs = """af,am,ar,ast,az,ba,be,bg,bn,br,bs,ca,ceb,cs,cy,da,de,el,en,es,et,fa,ff,fi,fr,fy,ga,gd,gl,gu,ha,he,hi,hr,ht,hu,hy,id,ig,ilo,is,it,ja,jv,ka,kk,km,kn,ko,lb,lg,ln,lo,lt,lv,mg,mk,ml,mn,mr,ms,my,ne,nl,no,ns,oc,or,pa,pl,ps,pt,ro,ru,sd,si,sk,sl,so,sq,sr,ss,su,sv,sw,ta,th,tl,tn,tr,uk,ur,uz,vi,wo,xh,yi,yo,zh,zu""" | |
| lang_list = 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" ) | |
| Info = gr.Markdown( "# [$hyoo_lingua](https://lingua.hyoo.ru/)" ) | |
| Translate.click( | |
| translate, | |
| inputs=[ Language, Source ], | |
| outputs=[Result], | |
| api_name="translate", | |
| ) | |
| app.launch( inline=True ) | |
| block.queue( concurrency_count=2 ) | |