Hugging Face Streamlit Translation Space

https://huggingface.co/spaces/TiberiuCristianLeon/StreamlitTranslate

Use of quotation marks in the different languages

Language	Level 1	Level 2	Level 3	Opening Unicode	Opening decimal	Closing Unicode	Closing decimal
Bulgarian	„...“	„...“	„...“	U+201E	8222	U+201C	8220
Croatian	„...”	‚...’	‚...’	U+201A	8218	U+2019	8217
Czech	„...“	‚...‘	»...«	U+00BB	187	U+00AB	171
Danish	»...«	»...«	»...«	U+00BB	187	U+00AB	171
Dutch	“...”	“...”	“...”	U+201C	8220	U+201D	8221
English	‘...’	“...”	‘...’	U+2018	8216	U+2019	8217
Estonian	„...“	„...“	„...“	U+201E	8222	U+201C	8220
Finnish	”...”	”...”	”...”	U+201D	8221	U+201D	8221
French	«...»	“...”	‘...’	U+2018	8216	U+2019	8217
German	„...“	‚...‘	‚...‘	U+201A	8218	U+2018	8216
Greek	«...»	“...”	‘...’	U+2018	8216	U+2019	8217
Hungarian	„...”	»...«	’...’	U+2019	8217	U+2019	8217
Irish	‘...’	“...”	‘...’	U+2018	8216	U+2019	8217
Italian	«...»	“...”	‘...’	U+2018	8216	U+2019	8217
Lithuanian	„...“	„...“	„...“	U+201E	8222	U+201C	8220
Latvian	“...”	“...”	“...”	U+201C	8220	U+201D	8221
Maltese	“...”	‘...’	“...”	U+201C	8220	U+201D	8221
Polish	„...”	»...«	‘...’	U+2018	8216	U+2019	8217
Portuguese	«...»	“...”	‘...’	U+2018	8216	U+2019	8217
Romanian	„...”	«...»	„...”	U+201E	8222	U+201D	8221
Slovak	„...“	‚...‘	«...»	U+00AB	171	U+00BB	187
Slovenian	„...“	‚...‘	‚...‘	U+201A	8218	U+2018	8216
Spanish	«...»	“...”	‘...’	U+2018	8216	U+2019	8217
Swedish	”...”	’...’	’...’	U+2019	8217	U+2019	8217

Reference: https://op.europa.eu/en/web/eu-vocabularies/formex/physical-specifications/character-encoding/use-of-quotation-marks-in-the-different-languages

.	Name	period (ISO: full stop)
	Unicode	002E
	UTF-8	2E
,	Name	comma
	Unicode	002C
	UTF-8	2C
;	Name	semicolon (NB: Different from "Greek question mark")
	Unicode	003B
	UTF-8	3B
:	Name	colon
	Unicode	003A
	UTF-8	3A
?	Name	question mark
	Unicode	003F
	UTF-8	3F
¿	Name	inverted question mark
	Unicode	00BF
	UTF-8	C2BF
!	Name	exclamation mark
	Unicode	0021
	UTF-8	21
¡	Name	inverted exclamation mark
	Unicode	00A1
	UTF-8	C2A1
;	Name	Greek question mark (NB: Different from semicolon)
	Unicode	037E
	UTF-8	CDBE
·	Name	Greek middle dot (NB: Used as semicolon)
	Unicode	0387
	UTF-8	CE87
·	Name	middle dot (NB: Should not be used instead of 0387)
	Unicode	00B7
	UTF-8	C2B7
(	Name	opening parenthesis (ISO: left parenthesis)
	Unicode	0028
	UTF-8	28
)	Name	closing parenthesis (ISO: right parenthesis)
	Unicode	0029
	UTF-8	29
[	Name	opening square bracket (ISO: left square bracket)
	Unicode	005B
	UTF-8	5B
]	Name	closing square bracket (ISO: right square bracket)
	Unicode	005D
	UTF-8	5D
{	Name	opening curly bracket (ISO: left curly bracket)
	Unicode	007B
	UTF-8	7B
}	Name	closing curly bracket (ISO: right curly bracket)
	Unicode	007D
	UTF-8	7D
〈	Name	left pointing angle bracket
	Unicode	2329
	UTF-8	E28CA9
〉	Name	right pointing angle bracket
	Unicode	232A
	UTF-8	E28CAA

Accidentology Glossary - Glosssar zur Unfallrekonstruktion - Reconstrucție în urma accidentelor - Glosar

 

EN	RO
LLM (large language models)	modele lingvistice de dimensiuni mari
MLLM (multimodal large language models)	modele lingvistice multimodale de dimensiuni mari
ANN (artificial neuronal network)	rețea artificială neuronală
CNN (convolutional neural network)	rețea neuronală convoluțională	faltungsneuronales Netz
bounding box	cadru de delimitare	Begrenzungsrahmen
confidences	imagine confidențială
EES (energy efficiency standards)	standarde de eficiență energetică	Energieeffizienz
low beam headlights	faruri cu lumină de întâlnire	Abblendlicht
turn left	vira la stânga
ADAS (Advanced Driver Assistance System)	sisteme avansate de asistență pentru șofer
ITS (Intelligent Transportation Systems)	Sisteme de transport inteligent
stiffness	rigiditate
crash	coliziune
velocity	viteză
motor vehicles	autovehicule
overtaking distance	distanță de depășire
handlebar	ghidon
traffic fatalities	accidente rutiere mortale
bonnet	capotă
hood lifters	ridicătoare de capotă
GIDAS (German In-Depth Accident Study)	studiu aprofundat privind accidentele din Germania
seriously injured	răniți grav
slightly injured	răniți ușor
rear-end crashes	accidente din spate
accute angle	unghi ascuțit
PTI (periodical technical inspection)	ITP (inspecția tehnică obligatorie)
forensics	criminalistică
BEV (battery electric vehicles)	vehicule pe baterii electrice
ICE (internal combustion engine)	motoare cu ardere internă
roadworthy	stare tehnică corespunzătoare
DTC (disgnostic trouble codes)	coduri de diagnosticare a erorilor
electric powertrain	propulsie electrică
traction battery	baterie de tracțiune
high-voltage wiring	cablaje de înaltă tensiune
failures	defectări
oncoming	venind din sens opus
towing	tractare
PSAP (Public Safety Answering Point)	Centru de răspuns pentru siguranța publică
enclosure	carcasă
OEM (Original Equipment Manufacturer)	Producători de echipamente originale
high strength material body components	componente ale caroseriei din materiale de înaltă rezistență
underbody	partea interioară a caroseriei
deployed airbags	airbag-uri declanșate
EES (Energy Equivalent Speed)	viteza echivalentă energetică
crumple zones	zone de deformare
crashworthiness	rezistență la impact
T-bode collisions	coliziuni frontale
rear-cross member	traversă spate
lamp post	stâlp de iluminat
deflection	deformare
indentation	indentare
jerk	smucitură
PONR (the Point of No Return)	punctul fără întoarcere
flatbed transit	transport cu platformă
allowance	toleranță
roadworthiness	stare tehnică
EDR (Event Data Recorder)	înregistrator de date de eveniment
CDR (Crash Data Retrieval)	recuperarea datelor în caz de accident
motorcars	automobile
elapse timing	timp de decurs
retardation	încetinire
slip	alunecare
RCM (restrain control module)	modulul de control al restricției
dash camera	cameră video pentru bord
to slid	a derapa
to cut off	a tăia fața
airstrip	pistă de aterizare
suction cupped to windscreen	ventuză pentru parbriz
dashboard	tablou de bord
onboard	înregistrat la bord
dash camera	cameră video pentru bord
left turn	viraj la stânga
VRU (Vulnerable Road Users)
shear force	forță de forfecare
bending moment	moment de încovoiere
occipital condyle	condil occipital
SPH (Smoothed Particle Hydrodynamics)
roundabounts	sensuri giratorii
single lane	bandă unică
road layout	traseu
seating	scaun
flat track	pistă plată
steearable front axle	puntea față direcționabilă
air bearings	rulmenți pneumatici
wear parts	piese de uzură
airsteam fan	ventilator cu abur
road tanker	autocisternă
shock dampener	amortizor
guardrails	parapete
curbs	borduri
keeling-over	a se răsturna
skid marks	urme de frânare
telescopic broom	braț telescopic
rig	platformă
rollover / tip over	răsturnare
2-wheelers	vehicule cu 2 roți
lashing strap	curea de fixare
lashing strap	curea de legare
tie-down lashing	fixare prin legare
semi-tailer	semi-remorcă
loadind bed	platforma de încărcare
accident reconstruction		Unfallrekonstruktion, Rekonstruktion des Unfallhergangs, Unfallhergangsanalyse
neuron		die Nervenzelle, das Neuron
neural network		neuronales Netzwerk
hidden layer		ausgeblendete Schicht
image classification		Bildklassifikation
clustering		Gruppierung
peer group		Bezugsgruppe, Referenzgruppe
overlay		Überlagerung
lens distortion		Objektivverzeichnung
whiplash		Schleudertrauma
verbose		wortreich
neck brace		Halsmanschette, Nackenbandage, Nackenstütze

Regex Localization Convertions

Source text	Target text	Regex find	Regex replace with
$218,480	218.480 $	\$(\d+)\,(\d+)	$1.$2 \$
€57.495	57.495 €	\€(\d.+\.\d.+)	$1 €

Python Script to Download Bergamot Models

import httpx

import tarfile

import os

from urllib.parse import urlparse

 

# https://data.statmt.org/bergamot/models/models.json

# List of model URLs

urls = [

"https://data.statmt.org/bergamot/models/csen/csen.student.base.v1.cd5418ba6a412fc7.tar.gz",

"https://data.statmt.org/bergamot/models/csen/csen.student.tiny11.v1.8f603aded58f0a3c.tar.gz",

"https://data.statmt.org/bergamot/models/csen/encs.student.base.v1.db770d87e491b0dc.tar.gz",

"https://data.statmt.org/bergamot/models/csen/encs.student.tiny11.v1.b5c1ff605296b0e5.tar.gz",

"https://data.statmt.org/bergamot/models/deen/deen.student.base.v2.caa7c0ce3c8eaf05.tar.gz",

"https://data.statmt.org/bergamot/models/deen/deen.student.tiny11.v2.9f70fcb17bf9572d.tar.gz",

"https://data.statmt.org/bergamot/models/deen/ende.student.base.v2.37b172bc9b594f9b.tar.gz",

"https://data.statmt.org/bergamot/models/deen/ende.student.tiny11.v2.93821e13b3c511b5.tar.gz",

"https://data.statmt.org/bergamot/models/esen/esen.student.tiny11.v1.09576f06d0ad805e.tar.gz",

"https://data.statmt.org/bergamot/models/esen/enes.student.tiny11.v1.a7203a8f8e9daea8.tar.gz",

"https://data.statmt.org/bergamot/models/eten/eten.student.tiny11.v1.38de61c668e42f36.tar.gz",

"https://data.statmt.org/bergamot/models/eten/enet.student.tiny11.v1.0b8f835b0c154aaa.tar.gz",

"https://data.statmt.org/bergamot/models/isen/isen.student.base.v2.536d6b8808a5c076.tar.gz",

"https://data.statmt.org/bergamot/models/isen/isen.student.tiny11.v2.829203cf37b7bdc4.tar.gz",

"https://data.statmt.org/bergamot/models/nben/nben.student.tiny11.v1.e410ce34f8337aab.tar.gz",

"https://data.statmt.org/bergamot/models/nnen/nnen.student.tiny11.v1.0efa37c16887eea4.tar.gz",

"https://data.statmt.org/bergamot/models/bgen/bgen.student.tiny11.v1.f9c89a3a25ff8dca.tar.gz",

"https://data.statmt.org/bergamot/models/bgen/enbg.student.tiny11.v1.3ea060c1b76470a7.tar.gz",

"https://data.statmt.org/bergamot/models/plen/plen.student.tiny11.v1.87148203cbda2842.tar.gz",

"https://data.statmt.org/bergamot/models/plen/enpl.student.tiny11.v1.c33219daa12e7872.tar.gz",

"https://data.statmt.org/bergamot/models/fren/fren.student.tiny11.v1.dccea16d03c0a389.tar.gz",

"https://data.statmt.org/bergamot/models/fren/enfr.student.tiny11.v1.805d112122af03d0.tar.gz",

"https://data.statmt.org/bergamot/models/hbseng/hbseng.student.tiny11.v1.fa8a29e01a5332ba.tar.gz",

"https://data.statmt.org/bergamot/models/slen/slen.student.tiny11.v1.d029034e49c3bb08.tar.gz",

"https://data.statmt.org/bergamot/models/mken/mken.student.tiny11.v1.dd03ef56f4695c7b.tar.gz",

"https://data.statmt.org/bergamot/models/mten/mten.student.tiny11.v1.4089a5a036eff1c3.tar.gz",

"https://data.statmt.org/bergamot/models/tren/tren.student.tiny11.v1.d7728d17a313230a.tar.gz",

"https://data.statmt.org/bergamot/models/sqen/sqen.student.tiny11.v1.6ead0c9b236f942b.tar.gz",

"https://data.statmt.org/bergamot/models/caen/caen.student.tiny11.v1.edaf67d1938e80d3.tar.gz",

"https://data.statmt.org/bergamot/models/elen/elen.student.tiny11.v1.0006442831596378.tar.gz",

"https://data.statmt.org/bergamot/models/uken/uken.student.tiny11.v1.108d04d1e160153a.tar.gz"

]

# Create a folder to store all models

os.makedirs("models", exist_ok=True)

for url in urls:

filename = os.path.basename(url)

folder_name = filename.replace(".tar.gz", "")

folder_path = os.path.join("models", folder_name)

os.makedirs(folder_path, exist_ok=True)

print(f"📥 Downloading {filename}...")

response = httpx.get(url)

archive_path = os.path.join(folder_path, filename)

with open(archive_path, "wb") as f:

f.write(response.content)

print(f"📦 Extracting to {folder_path}...")

with tarfile.open(archive_path, "r:gz") as tar:

tar.extractall(path=folder_path)

os.remove(archive_path)

print(f"✅ Done: {folder_name}\n")

print("🎉 All models downloaded and extracted!")

Bergamot Translator Linux and Python - Bergamot and TranslateLocally Models

Running bergamot-translator on Linux

$ git clone git@github.com:browsermt/bergamot-translator.git
$ mkdir build
$ sudo apt install libpcre2-dev libopenblas-dev
$ cmake ..
$ make -j

yaml file:

bergamot-mode: native
models:
  - firefox-translations-models/models/prod/esen/model.esen.intgemm.alphas.bin
vocabs:
  - firefox-translations-models/models/prod/esen/vocab.esen.spm
  - firefox-translations-models/models/prod/esen/vocab.esen.spm
shortlist:
    - firefox-translations-models/models/prod/esen/lex.50.50.esen.s2t.bin
    - false
beam-size: 1
normalize: 1.0
word-penalty: 0
max-length-break: 128
mini-batch-words: 1024
workspace: 128
max-length-factor: 2.0
skip-cost: true
cpu-threads: 0
quiet: false
quiet-translation: false
gemm-precision: int8shiftAlphaAll
alignment: soft 

where esen is the language pair for the translation, in this case es→en (Spanish to English).

The models/vocabs/shortlist files should be sourced from the firefox-translations-models repository, with git-lfs. There's some docs which still point to Google cloud storage for downloads, but those are stale.

Pipe some data through bergamot-translator:

echo "Hola mundo" | ./bergamot-translator --model-config-paths config.yml

---

Requirement: Python <= 3.10 (wheels are not available for newer versions)

pip install bergamot

import bergamot

config = bergamot.ServiceConfig(numWorkers=4)
service = bergamot.Service(config)
model = service.modelFromConfigPath("bergamot.config.yml")
options = bergamot.ResponseOptions(
    alignment=False, qualityScores=False, HTML=False
)
response = service.translate(model, bergamot.VectorString([
    "In the last 3 months, over 80 arrestees were released from the Central Booking facility without being formally charged.",
    "Since its inception, The Onion has become a veritable news parody empire.",
    "The hostel’s guests were mostly citizens of the United Arab Emirates.",
]), options)

for r in response:
    print(r.target.text)
 

bergamot.config.yml:

# To imitate production setting, these Marian options are set according to
# https://github.com/mozilla/firefox-translations/blob/main/extension/controller/translation/translationWorker.js
# For reference, see https://github.com/mozilla/firefox-translations-models/blob/main/evals/translators/bergamot.sh

bergamot-mode: wasm
models:
  - ./model.enro.intgemm.alphas.bin
vocabs:
  - ./vocab.enro.spm
  - ./vocab.enro.spm
shortlist:
    - ./lex.50.50.enro.s2t.bin
    - false
beam-size: 1
normalize: 1.0
word-penalty: 0
max-length-break: 128
mini-batch-words: 1024
workspace: 128
max-length-factor: 2.0
skip-cost: true
cpu-threads: 4
quiet: false
quiet-translation: false
gemm-precision: int8shiftAlphaAll
alignment: soft 

Translatelocally compatible models:

https://translatelocally.com/models.json

Firefox models:

https://github.com/mozilla/firefox-translations-models/tree/main/models 

Glosar Energie DERO

 

Heizkraftwerk	centrală termică de încălzire
Abbaurate	rată de descompunere
Abfallbehandlunsanlage	instalaţie de tratare a reziduurilor
Abgabe	transmitere
Absorber	instalaţie de absorbţie
Additiv	aditiv
Altholzsortimente	sortimente de lemn utilizat
anfallend	apărut
Anlieferung	livrare
Annahmebereich	zonă de alimentare
Aufbereitungsanlage	instalaţie de tratare
Ausbeute	exploatare
Ausbringung	evacuare
Ausgangssstoff	materie primă
Basismaterial	material de bază
Bedienkomfort	confort de utilizare
BHKW	unitate de cogenerare
Bioabfall	resturi vegetale
Biogas	biogaz
Biomasse	biomasă
Blockheizkraftwerk	centrală termică combinată
Brikettierungsanlagen	instalaţii de brichetare
Bunker	buncăr
CO2-Ausstoß	evacuare CO2
CO2-neutral	fără CO2
combined heat and power / Kraft-Wärme-Kopplung	CHP / cogenerare
Dampfaustausch	schimb de aburi
Dampfkessel	cazan cu aburi
Deponie	depozit de reziduuri
Deponiefraktion	fracţiunea depozitului de reziduuri
Durchforstung	rărirea arboretului
Eigenkapitalbeschaffung	procurarea capitalului propriu
Einkommensquelle	sursă de venit
eisenhaltig	feros
Elektrizitätsnetz	reţea de electricitate
Emissionsgrenzwert	valoare limită a emisiilor
Endlager	depozit final
Energiepflanze	plantă energetică
Energieträger	suport energetic
Energieversorgungskonzept	concept de alimentare cu energie
entschwefelt	desulfurizat
erneubar	regenerabil
Ersatzbrennstoff	combustibil alternativ
Fassungsvermögen	capacitate
Faulraum	autoclavă [ch.]
Faulraum	autoclavă de devulcanizare
Faulraum	bazin de fermentare
Faulraum	cazan fierbător
Faulraum	devulcanizator
Faulraum	digestor [plast.]
Faulraum	fierbător [term.]
Ferment	ferment
Fermenter	fermenter
Festmist	gunoi solid de grajd
Feststoff	material solid
Feuerraum	cameră de ardere
Feuerraum	focar
Feuerwärmeleistung	putere calorică de ardere
Flotatfett	grăsime de flotaţie
fossile Energiequelle	sursă fosilă de energie
Frischdampf	abur proaspăt
Gärrestlager	depozit pentru resturile de fermentare
gasdicht	etanş
Gasertrag	debit de gaz, producţie de gaz
Gaslager	depozit de acumulare a gazelor
Getreidespelzen	pleavă de cereale
Großflügelrührwerk	malaxor cu pale de mari dimensiuni
Grünschnittpellets	pelete din tăierea plantelor
Gülle	must de bălegar
Halogenverbindung	compus cu halogen
Hausmüll	gunoi menajer
Heizöl	combustibil lichid de încãlzire
Heizöl	păcură
Hochdruckdampfkessel	cazan cu aburi de înaltă presiune
Holzbriketts	brichete de lemn
Inputstoff	material de input
Kesselhaus	sala cazanelor
Kesselwasser	apă din cazan
Klärschlamm	nămol de la staţia de epurare
Kleinfeuerungsanlagen	instalaţii de ardere de mici dimensiuni
klimaschädlich	dăunător climei
Kohlekraftwerk	centrală termică pe cărbuni
Kohlendioxid	dioxid de carbon
Kondensat	condens
konventionelles Kraftwerk	centrală termică convenţională
Konvertierung	convertire
Kraft-Wärme-Koppelungseinheiten	unităţi de cogenerare
Kraft-Wärme-Kopplung	cuplare curent-căldură
Kraft-Wärme-Kopplung / KWK	cogenerare
Landschaftspflege	amenajarea peisajului
Luftkondensator	condensator de aer
Maissilage	însilozarea porumbului
Maschinenhaus	sala maşinilor
Methan	metan
mikrobiell	microbian
Mist	gunoi de grajd
Nachgärer	fermenter secundar
Nachgärung	fermentare ulterioară
Nachwachsende Rohstoffe	resurse primare regenerabile
naturbelassenen Biomassen	biomase naturale
NaWaRo	resurse primare regenerabile
Nebenprodukt	produs auxiliar
nicht eisenhaltig	neferos
Nutzvolumen	volum util
Olivenkern	sâmbure de măsline
organische Reststoffe	resturi organice
Pelletheizung	încălzire cu peleţi
Pelletierung	peletizare
Preisspirale	spirala preţurilor
Privathaushalt	gospodărie privată
Produktionsablauf	desfăşurarea producţiei
Produktionsstandort	locaţie de producţie
Prozesoptimierung	optimizarea producţiei
Prozessdamf	abur de proces
Prozesswasser	apă de proces
Pumpsystem	sistem de pompare
Rauchgas	gaz de ardere
Reaktionsturm	turn de reacţie
refuse-derived fuel	RDF
regenerativ	regenerativ
Restholz	resturi de material lemnos
Rindenbriketts	birichete din coajă de lemn
Rohfaser	fibră brută
Rohrschlange	serpentină din ţeavă
Rost	grilaj
Rostschlacke	zgură
sauerstofffrei	anaerob
Saugzug	tiraj artificial
Saugzug	tiraj forţat
Schadstoff	substanţă dăunătoară
Schadstoffe	noxe
Schallschutzcontainer	container cu protecţie fonică
Schlackebunker	buncăr pentru zgură
Schlauchfilter	filtru cu furtun
Schwefeloxid	oxid de sulf
Schwermetall	metal greu
Schwermetalle	metale grele
Sekundärluft	aer secundar
Silage	însilozare
Silo	siloz
Speiseabfälle	resturi alimentare
Speisereste	resturi alimentare
Speisewasser	apă de alimentare
Spurengas	gaz remanent
Stickgas	azot
Stickoxid	oxid de azot
Stickstoff	azot
Stößel	bătător
Stößel	berbec de sonetă
Stößel	tachet
Stößel	cap de mortezat
Stößel	pisălog
Strauchschnitt	tăierea arbuştilor
Strombedarf	necesar de curent
substituieren	substitui
Substrat	substrat
Symbiose	simbioză
Tauchmotor	motor submersibil
Treibhausgas	gaz de seră
Turbine	turbină
Turbogeneratorsatz	unitate turbogeneratoare
unter Luftabschluss	fără aer
Verbrennungsprozess	proces de ardere
Vergärung	fermentare
Versorger	companie de alimentare cu energie
Verweildauer	durată de menţinere
Verwertung	valorificare
Vorgrube	rezervor preliminar
Waldrestholz	resturi de lemn din pădure
Wärmetäuscher	schimbător de căldură
Wasserbad	baie de apă
Wertschöpfungskette	lanţ de valoare adăugată
Wirtschaftsdünger	îngrăşăminte economice
Wirtschaftsdünger	fertlizant industrial
zersetzen	descompune
Zufeuerung zu fossilen Brennstoffen	co-firing / combustie combinată cu combustibili fosili
Zersetzung	descompunere