Spaces:
Running
Running
File size: 12,051 Bytes
4e82fb6 9cf2e86 4e82fb6 67cc6b1 4e82fb6 67cc6b1 4e82fb6 9cf2e86 ccf78ae 4e82fb6 9cf2e86 ccf78ae 9cf2e86 67cc6b1 a70c074 67cc6b1 a70c074 67cc6b1 ccf78ae 67cc6b1 ccf78ae 67cc6b1 4e82fb6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
import gradio as gr
import torch
import os
from datetime import datetime
from .base_interface import BaseInterface
from modules.subtitle_manager import *
DEFAULT_MODEL_SIZE = "facebook/nllb-200-1.3B"
NLLB_MODELS = ["facebook/nllb-200-3.3B", "facebook/nllb-200-1.3B", "facebook/nllb-200-distilled-600M"]
class NLLBInference(BaseInterface):
def __init__(self):
super().__init__()
self.default_model_size = DEFAULT_MODEL_SIZE
self.current_model_size = None
self.model = None
self.tokenizer = None
self.available_models = NLLB_MODELS
self.available_source_langs = list(NLLB_AVAILABLE_LANGS.keys())
self.available_target_langs = list(NLLB_AVAILABLE_LANGS.keys())
self.device = 0 if torch.cuda.is_available() else -1
self.pipeline = None
def translate_text(self, text):
result = self.pipeline(text)
return result[0]['translation_text']
def translate_file(self,
fileobjs: list,
model_size: str,
src_lang: str,
tgt_lang: str,
add_timestamp: bool,
progress=gr.Progress()):
"""
Translate subtitle file from source language to target language
Parameters
----------
fileobjs: list
List of files to transcribe from gr.Files()
model_size: str
Whisper model size from gr.Dropdown()
src_lang: str
Source language of the file to translate from gr.Dropdown()
tgt_lang: str
Target language of the file to translate from gr.Dropdown()
add_timestamp: bool
Boolean value from gr.Checkbox() that determines whether to add a timestamp at the end of the filename.
progress: gr.Progress
Indicator to show progress directly in gradio.
I use a forked version of whisper for this. To see more info : https://github.com/jhj0517/jhj0517-whisper/tree/add-progress-callback
"""
try:
if model_size != self.current_model_size or self.model is None:
print("\nInitializing NLLB Model..\n")
progress(0, desc="Initializing NLLB Model..")
self.current_model_size = model_size
self.model = AutoModelForSeq2SeqLM.from_pretrained(pretrained_model_name_or_path=model_size,
cache_dir=os.path.join("models", "NLLB"))
self.tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_size,
cache_dir=os.path.join("models", "NLLB", "tokenizers"))
src_lang = NLLB_AVAILABLE_LANGS[src_lang]
tgt_lang = NLLB_AVAILABLE_LANGS[tgt_lang]
self.pipeline = pipeline("translation",
model=self.model,
tokenizer=self.tokenizer,
src_lang=src_lang,
tgt_lang=tgt_lang,
device=self.device)
files_info = {}
for fileobj in fileobjs:
file_path = fileobj.name
file_name, file_ext = os.path.splitext(os.path.basename(fileobj.orig_name))
if file_ext == ".srt":
parsed_dicts = parse_srt(file_path=file_path)
total_progress = len(parsed_dicts)
for index, dic in enumerate(parsed_dicts):
progress(index / total_progress, desc="Translating..")
translated_text = self.translate_text(dic["sentence"])
dic["sentence"] = translated_text
subtitle = get_serialized_srt(parsed_dicts)
timestamp = datetime.now().strftime("%m%d%H%M%S")
if add_timestamp:
output_path = os.path.join("outputs", "translations", f"{file_name}-{timestamp}")
else:
output_path = os.path.join("outputs", "translations", f"{file_name}")
write_file(subtitle, f"{output_path}.srt")
elif file_ext == ".vtt":
parsed_dicts = parse_vtt(file_path=file_path)
total_progress = len(parsed_dicts)
for index, dic in enumerate(parsed_dicts):
progress(index / total_progress, desc="Translating..")
translated_text = self.translate_text(dic["sentence"])
dic["sentence"] = translated_text
subtitle = get_serialized_vtt(parsed_dicts)
timestamp = datetime.now().strftime("%m%d%H%M%S")
if add_timestamp:
output_path = os.path.join("outputs", "translations", f"{file_name}-{timestamp}")
else:
output_path = os.path.join("outputs", "translations", f"{file_name}")
write_file(subtitle, f"{output_path}.vtt")
files_info[file_name] = subtitle
total_result = ''
for file_name, subtitle in files_info.items():
total_result += '------------------------------------\n'
total_result += f'{file_name}\n\n'
total_result += f'{subtitle}'
return f"Done! Subtitle is in the outputs/translation folder.\n\n{total_result}"
except Exception as e:
return f"Error: {str(e)}"
finally:
self.release_cuda_memory()
self.remove_input_files([fileobj.name for fileobj in fileobjs])
NLLB_AVAILABLE_LANGS = {
"Acehnese (Arabic script)": "ace_Arab",
"Acehnese (Latin script)": "ace_Latn",
"Mesopotamian Arabic": "acm_Arab",
"Ta’izzi-Adeni Arabic": "acq_Arab",
"Tunisian Arabic": "aeb_Arab",
"Afrikaans": "afr_Latn",
"South Levantine Arabic": "ajp_Arab",
"Akan": "aka_Latn",
"Amharic": "amh_Ethi",
"North Levantine Arabic": "apc_Arab",
"Modern Standard Arabic": "arb_Arab",
"Modern Standard Arabic (Romanized)": "arb_Latn",
"Najdi Arabic": "ars_Arab",
"Moroccan Arabic": "ary_Arab",
"Egyptian Arabic": "arz_Arab",
"Assamese": "asm_Beng",
"Asturian": "ast_Latn",
"Awadhi": "awa_Deva",
"Central Aymara": "ayr_Latn",
"South Azerbaijani": "azb_Arab",
"North Azerbaijani": "azj_Latn",
"Bashkir": "bak_Cyrl",
"Bambara": "bam_Latn",
"Balinese": "ban_Latn",
"Belarusian": "bel_Cyrl",
"Bemba": "bem_Latn",
"Bengali": "ben_Beng",
"Bhojpuri": "bho_Deva",
"Banjar (Arabic script)": "bjn_Arab",
"Banjar (Latin script)": "bjn_Latn",
"Standard Tibetan": "bod_Tibt",
"Bosnian": "bos_Latn",
"Buginese": "bug_Latn",
"Bulgarian": "bul_Cyrl",
"Catalan": "cat_Latn",
"Cebuano": "ceb_Latn",
"Czech": "ces_Latn",
"Chokwe": "cjk_Latn",
"Central Kurdish": "ckb_Arab",
"Crimean Tatar": "crh_Latn",
"Welsh": "cym_Latn",
"Danish": "dan_Latn",
"German": "deu_Latn",
"Southwestern Dinka": "dik_Latn",
"Dyula": "dyu_Latn",
"Dzongkha": "dzo_Tibt",
"Greek": "ell_Grek",
"English": "eng_Latn",
"Esperanto": "epo_Latn",
"Estonian": "est_Latn",
"Basque": "eus_Latn",
"Ewe": "ewe_Latn",
"Faroese": "fao_Latn",
"Fijian": "fij_Latn",
"Finnish": "fin_Latn",
"Fon": "fon_Latn",
"French": "fra_Latn",
"Friulian": "fur_Latn",
"Nigerian Fulfulde": "fuv_Latn",
"Scottish Gaelic": "gla_Latn",
"Irish": "gle_Latn",
"Galician": "glg_Latn",
"Guarani": "grn_Latn",
"Gujarati": "guj_Gujr",
"Haitian Creole": "hat_Latn",
"Hausa": "hau_Latn",
"Hebrew": "heb_Hebr",
"Hindi": "hin_Deva",
"Chhattisgarhi": "hne_Deva",
"Croatian": "hrv_Latn",
"Hungarian": "hun_Latn",
"Armenian": "hye_Armn",
"Igbo": "ibo_Latn",
"Ilocano": "ilo_Latn",
"Indonesian": "ind_Latn",
"Icelandic": "isl_Latn",
"Italian": "ita_Latn",
"Javanese": "jav_Latn",
"Japanese": "jpn_Jpan",
"Kabyle": "kab_Latn",
"Jingpho": "kac_Latn",
"Kamba": "kam_Latn",
"Kannada": "kan_Knda",
"Kashmiri (Arabic script)": "kas_Arab",
"Kashmiri (Devanagari script)": "kas_Deva",
"Georgian": "kat_Geor",
"Central Kanuri (Arabic script)": "knc_Arab",
"Central Kanuri (Latin script)": "knc_Latn",
"Kazakh": "kaz_Cyrl",
"Kabiyè": "kbp_Latn",
"Kabuverdianu": "kea_Latn",
"Khmer": "khm_Khmr",
"Kikuyu": "kik_Latn",
"Kinyarwanda": "kin_Latn",
"Kyrgyz": "kir_Cyrl",
"Kimbundu": "kmb_Latn",
"Northern Kurdish": "kmr_Latn",
"Kikongo": "kon_Latn",
"Korean": "kor_Hang",
"Lao": "lao_Laoo",
"Ligurian": "lij_Latn",
"Limburgish": "lim_Latn",
"Lingala": "lin_Latn",
"Lithuanian": "lit_Latn",
"Lombard": "lmo_Latn",
"Latgalian": "ltg_Latn",
"Luxembourgish": "ltz_Latn",
"Luba-Kasai": "lua_Latn",
"Ganda": "lug_Latn",
"Luo": "luo_Latn",
"Mizo": "lus_Latn",
"Standard Latvian": "lvs_Latn",
"Magahi": "mag_Deva",
"Maithili": "mai_Deva",
"Malayalam": "mal_Mlym",
"Marathi": "mar_Deva",
"Minangkabau (Arabic script)": "min_Arab",
"Minangkabau (Latin script)": "min_Latn",
"Macedonian": "mkd_Cyrl",
"Plateau Malagasy": "plt_Latn",
"Maltese": "mlt_Latn",
"Meitei (Bengali script)": "mni_Beng",
"Halh Mongolian": "khk_Cyrl",
"Mossi": "mos_Latn",
"Maori": "mri_Latn",
"Burmese": "mya_Mymr",
"Dutch": "nld_Latn",
"Norwegian Nynorsk": "nno_Latn",
"Norwegian Bokmål": "nob_Latn",
"Nepali": "npi_Deva",
"Northern Sotho": "nso_Latn",
"Nuer": "nus_Latn",
"Nyanja": "nya_Latn",
"Occitan": "oci_Latn",
"West Central Oromo": "gaz_Latn",
"Odia": "ory_Orya",
"Pangasinan": "pag_Latn",
"Eastern Panjabi": "pan_Guru",
"Papiamento": "pap_Latn",
"Western Persian": "pes_Arab",
"Polish": "pol_Latn",
"Portuguese": "por_Latn",
"Dari": "prs_Arab",
"Southern Pashto": "pbt_Arab",
"Ayacucho Quechua": "quy_Latn",
"Romanian": "ron_Latn",
"Rundi": "run_Latn",
"Russian": "rus_Cyrl",
"Sango": "sag_Latn",
"Sanskrit": "san_Deva",
"Santali": "sat_Olck",
"Sicilian": "scn_Latn",
"Shan": "shn_Mymr",
"Sinhala": "sin_Sinh",
"Slovak": "slk_Latn",
"Slovenian": "slv_Latn",
"Samoan": "smo_Latn",
"Shona": "sna_Latn",
"Sindhi": "snd_Arab",
"Somali": "som_Latn",
"Southern Sotho": "sot_Latn",
"Spanish": "spa_Latn",
"Tosk Albanian": "als_Latn",
"Sardinian": "srd_Latn",
"Serbian": "srp_Cyrl",
"Swati": "ssw_Latn",
"Sundanese": "sun_Latn",
"Swedish": "swe_Latn",
"Swahili": "swh_Latn",
"Silesian": "szl_Latn",
"Tamil": "tam_Taml",
"Tatar": "tat_Cyrl",
"Telugu": "tel_Telu",
"Tajik": "tgk_Cyrl",
"Tagalog": "tgl_Latn",
"Thai": "tha_Thai",
"Tigrinya": "tir_Ethi",
"Tamasheq (Latin script)": "taq_Latn",
"Tamasheq (Tifinagh script)": "taq_Tfng",
"Tok Pisin": "tpi_Latn",
"Tswana": "tsn_Latn",
"Tsonga": "tso_Latn",
"Turkmen": "tuk_Latn",
"Tumbuka": "tum_Latn",
"Turkish": "tur_Latn",
"Twi": "twi_Latn",
"Central Atlas Tamazight": "tzm_Tfng",
"Uyghur": "uig_Arab",
"Ukrainian": "ukr_Cyrl",
"Umbundu": "umb_Latn",
"Urdu": "urd_Arab",
"Northern Uzbek": "uzn_Latn",
"Venetian": "vec_Latn",
"Vietnamese": "vie_Latn",
"Waray": "war_Latn",
"Wolof": "wol_Latn",
"Xhosa": "xho_Latn",
"Eastern Yiddish": "ydd_Hebr",
"Yoruba": "yor_Latn",
"Yue Chinese": "yue_Hant",
"Chinese (Simplified)": "zho_Hans",
"Chinese (Traditional)": "zho_Hant",
"Standard Malay": "zsm_Latn",
"Zulu": "zul_Latn",
}
|