File size: 1,535 Bytes
ac8cea6
 
 
 
 
 
 
6fa74a8
 
ac8cea6
8a51e80
ac8cea6
 
 
 
 
 
 
676dadb
ac8cea6
 
 
 
 
 
 
 
 
 
 
 
75a2980
ac8cea6
 
75a2980
ac8cea6
75a2980
ac8cea6
 
 
5e420cc
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
import os
import torch
import gradio as gr
import time
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline


model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-1.3B")
tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-1.3B")

def translation(source, target, text) -> str:

    translator = pipeline('translation', model=model, tokenizer=tokenizer, src_lang=source, tgt_lang=target)
    output = translator(text, max_length=400)

    end_time = time.time()

    output = output[0]['translation_text']
    return output


if __name__ == '__main__':
    
    # define gradio demo
    lang_codes = ["eng_Latn", "fuv_Latn", "fra_Latn", "arb_Arab"]
    #inputs = [gr.inputs.Radio(['nllb-distilled-600M', 'nllb-1.3B', 'nllb-distilled-1.3B'], label='NLLB Model'),
    inputs = [gr.inputs.Dropdown(lang_codes, default='fra_Latn', label='Source'),
              gr.inputs.Dropdown(lang_codes, default='fuv_Latn', label='Target'),
              gr.inputs.Textbox(lines=5, label="Input text"),
              ]

    title = "Fulfulde translator"

    demo_status = "Demo is running on CPU"
    description = "Fulfulde to French, English or Arabic and vice-versa translation demo using NLLB."
    examples = [
    ['fra_Latn', 'fuv_Latn', 'La traduction est une tâche facile.']
    ]


    gr.Interface(
        translation,
        inputs,
        ["text"],
        examples=examples,
        cache_examples=False,
        title=title,
        description=description
    ).launch()