Duplicate from 511KeV/nllb-translation-demo

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Nllb Translation Demo
+emoji: 👀
+colorFrom: indigo
+colorTo: green
+sdk: gradio
+sdk_version: 3.0.26
+app_file: app.py
+pinned: false
+duplicated_from: 511KeV/nllb-translation-demo
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,88 @@
+import os
+import torch
+import gradio as gr
+import time
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from flores200_codes import flores_codes
+
+#print(f"Is CUDA available: {torch.cuda.is_available()}")
+# True
+#print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
+
+def load_models():
+    # build model and tokenizer
+    model_name_dict = {'nllb-distilled-600M': 'facebook/nllb-200-distilled-600M',
+                  #'nllb-1.3B': 'facebook/nllb-200-1.3B',
+                  #'nllb-distilled-1.3B': 'facebook/nllb-200-distilled-1.3B',
+                  #'nllb-3.3B': 'facebook/nllb-200-3.3B',
+                  }
+
+    model_dict = {}
+
+    for call_name, real_name in model_name_dict.items():
+        print('\tLoading model: %s' % call_name)
+        model = AutoModelForSeq2SeqLM.from_pretrained(real_name)
+        tokenizer = AutoTokenizer.from_pretrained(real_name)
+        model_dict[call_name+'_model'] = model
+        model_dict[call_name+'_tokenizer'] = tokenizer
+
+    return model_dict
+
+
+def translation(source, target, text):
+    if len(model_dict) == 2:
+        model_name = 'nllb-distilled-600M'
+
+    start_time = time.time()
+    source = flores_codes[source]
+    target = flores_codes[target]
+
+    model = model_dict[model_name + '_model']
+    tokenizer = model_dict[model_name + '_tokenizer']
+
+    translator = pipeline('translation', model=model, tokenizer=tokenizer, src_lang=source, tgt_lang=target)
+    output = translator(text, max_length=4098)
+
+    end_time = time.time()
+
+    output = output[0]['translation_text']
+    result = {'inference_time': end_time - start_time,
+              'source': source,
+              'target': target,
+              'result': output}
+    return result
+
+
+if __name__ == '__main__':
+    print('\tinit models')
+
+    global model_dict
+
+    model_dict = load_models()
+    
+    # define gradio demo
+    lang_codes = list(flores_codes.keys())
+    #inputs = [gr.inputs.Radio(['nllb-distilled-600M', 'nllb-1.3B', 'nllb-distilled-1.3B'], label='NLLB Model'),
+    inputs = [gr.inputs.Dropdown(lang_codes, default='English', label='Source'),
+              gr.inputs.Dropdown(lang_codes, default='Kashmiri', label='Target'),
+              gr.inputs.Textbox(lines=5, label="Input text"),
+              ]
+
+    outputs = gr.outputs.JSON()
+
+    title = "NLLB distilled 600M demo"
+
+    demo_status = "Demo is running on CPU"
+    description = f"Details: https://github.com/facebookresearch/fairseq/tree/nllb. {demo_status}"
+    examples = [
+    ['English', 'Kashmiri', 'Hi. nice to meet you']
+    ]
+
+    gr.Interface(translation,
+                 inputs,
+                 outputs,
+                 title=title,
+                 description=description,
+                 ).launch()
+
+

flores200_codes.py

@@ -0,0 +1,210 @@
+codes_as_string = '''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	kas_Arab
+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'''
+
+codes_as_string = codes_as_string.split('\n')
+
+flores_codes = {}
+for code in codes_as_string:
+    lang, lang_code = code.split('\t')
+    flores_codes[lang] = lang_code

imp.js

@@ -0,0 +1,2 @@
+import nllb-200-distilled-600M
+import nllb-200-3.3B

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/huggingface/transformers
+gradio
+torch