File size: 4,135 Bytes
3fce624 caccbf7 1c69775 c069c11 3fce624 1c69775 3fce624 caccbf7 1c69775 3fce624 4dffb82 1c69775 8877cce c069c11 1c69775 caccbf7 3fce624 8877cce 4dffb82 8877cce caccbf7 1c69775 8877cce 1c69775 4dffb82 caccbf7 1c69775 8877cce 1c69775 8877cce 4dffb82 1c69775 caccbf7 |
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 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 |
# Based on example code of https://huggingface.co/facebook/m2m100_1.2B
import gradio as gr
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
model = M2M100ForConditionalGeneration.from_pretrained(
"facebook/m2m100_1.2B")
tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_1.2B")
this_description = '''
Using facebook/m2m100_1.2B pre-trained model.
Chinese(zh)
English(en)
Hindi(hi)
Japanese(ja)
Sinhalese(si)
Thai(th)
Vietnamese(vi)
...
'''
# From facebook/m2m100_1.2B
lang_codes = {
"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": "oc",
"Oriya": "or",
"Panjabi; Punjabi": "pa",
"Polish": "pl",
"Pushto": "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"
}
def m2m_translate(Input_Text, from_lang, to_lang):
tokenizer.src_lang = lang_codes[from_lang]
encoded_from_lang = tokenizer(Input_Text, return_tensors="pt")
generated_tokens = model.generate(
**encoded_from_lang,
max_new_tokens=200,
forced_bos_token_id=tokenizer.get_lang_id(lang_codes[to_lang])
)
res = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
return res[0]
iface = gr.Interface(
fn=m2m_translate,
title="M2M100 Text Translation",
description=this_description,
inputs=[
gr.Textbox(lines=5, placeholder="Enter text", label="Text input"),
gr.Radio(
choices=[
'Burmese',
'Chinese',
'English',
'Hindi',
'Japanese',
'Sinhala',
'Thai',
'Vietnamese'
],
value='Vietnamese',
label='From language'
),
gr.Radio(
choices=[
'Burmese',
'Chinese',
'English',
'Hindi',
'Japanese',
'Sinhala',
'Thai',
'Vietnamese'
],
value='English',
label='To language'
),
],
outputs="text")
iface.launch()
|