translation

.gitignore

@@ -0,0 +1,180 @@
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# CMake
+cmake-build-*/
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+flagged/
+.idea*
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/aws.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="accountSettings">
+    <option name="activeProfile" value="profile:default" />
+    <option name="activeRegion" value="eu-west-1" />
+    <option name="recentlyUsedProfiles">
+      <list>
+        <option value="profile:default" />
+      </list>
+    </option>
+    <option name="recentlyUsedRegions">
+      <list>
+        <option value="eu-west-1" />
+      </list>
+    </option>
+  </component>
+</project>

.idea/csv-plugin.xml

@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="CsvFileAttributes">
+    <option name="attributeMap">
+      <map>
+        <entry key="/flagged/log.csv">
+          <value>
+            <Attribute>
+              <option name="separator" value="," />
+            </Attribute>
+          </value>
+        </entry>
+      </map>
+    </option>
+  </component>
+</project>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,110 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="75">
+            <item index="0" class="java.lang.String" itemvalue="PyMuPDF" />
+            <item index="1" class="java.lang.String" itemvalue="opencv-python-headless" />
+            <item index="2" class="java.lang.String" itemvalue="python-crfsuite" />
+            <item index="3" class="java.lang.String" itemvalue="greenlet" />
+            <item index="4" class="java.lang.String" itemvalue="joblib" />
+            <item index="5" class="java.lang.String" itemvalue="threadpoolctl" />
+            <item index="6" class="java.lang.String" itemvalue="scikit-learn" />
+            <item index="7" class="java.lang.String" itemvalue="python-dateutil" />
+            <item index="8" class="java.lang.String" itemvalue="py" />
+            <item index="9" class="java.lang.String" itemvalue="html2text" />
+            <item index="10" class="java.lang.String" itemvalue="MarkupSafe" />
+            <item index="11" class="java.lang.String" itemvalue="srsly" />
+            <item index="12" class="java.lang.String" itemvalue="mongoengine" />
+            <item index="13" class="java.lang.String" itemvalue="spacy" />
+            <item index="14" class="java.lang.String" itemvalue="certifi" />
+            <item index="15" class="java.lang.String" itemvalue="soupsieve" />
+            <item index="16" class="java.lang.String" itemvalue="gevent" />
+            <item index="17" class="java.lang.String" itemvalue="pydantic" />
+            <item index="18" class="java.lang.String" itemvalue="Flask-Script" />
+            <item index="19" class="java.lang.String" itemvalue="Werkzeug" />
+            <item index="20" class="java.lang.String" itemvalue="Flask-WTF" />
+            <item index="21" class="java.lang.String" itemvalue="zope.interface" />
+            <item index="22" class="java.lang.String" itemvalue="plac" />
+            <item index="23" class="java.lang.String" itemvalue="typing-extensions" />
+            <item index="24" class="java.lang.String" itemvalue="gunicorn" />
+            <item index="25" class="java.lang.String" itemvalue="pathy" />
+            <item index="26" class="java.lang.String" itemvalue="catalogue" />
+            <item index="27" class="java.lang.String" itemvalue="attrs" />
+            <item index="28" class="java.lang.String" itemvalue="simplejson" />
+            <item index="29" class="java.lang.String" itemvalue="cymem" />
+            <item index="30" class="java.lang.String" itemvalue="murmurhash" />
+            <item index="31" class="java.lang.String" itemvalue="idna" />
+            <item index="32" class="java.lang.String" itemvalue="wasabi" />
+            <item index="33" class="java.lang.String" itemvalue="flask-mongoengine" />
+            <item index="34" class="java.lang.String" itemvalue="pluggy" />
+            <item index="35" class="java.lang.String" itemvalue="cloudpickle" />
+            <item index="36" class="java.lang.String" itemvalue="numpy" />
+            <item index="37" class="java.lang.String" itemvalue="requests" />
+            <item index="38" class="java.lang.String" itemvalue="spacy-legacy" />
+            <item index="39" class="java.lang.String" itemvalue="Jinja2" />
+            <item index="40" class="java.lang.String" itemvalue="parsedatetime" />
+            <item index="41" class="java.lang.String" itemvalue="preshed" />
+            <item index="42" class="java.lang.String" itemvalue="smart-open" />
+            <item index="43" class="java.lang.String" itemvalue="blis" />
+            <item index="44" class="java.lang.String" itemvalue="urllib3" />
+            <item index="45" class="java.lang.String" itemvalue="itsdangerous" />
+            <item index="46" class="java.lang.String" itemvalue="zope.event" />
+            <item index="47" class="java.lang.String" itemvalue="scipy" />
+            <item index="48" class="java.lang.String" itemvalue="pymongo" />
+            <item index="49" class="java.lang.String" itemvalue="six" />
+            <item index="50" class="java.lang.String" itemvalue="typer" />
+            <item index="51" class="java.lang.String" itemvalue="Flask-Cors" />
+            <item index="52" class="java.lang.String" itemvalue="pytest" />
+            <item index="53" class="java.lang.String" itemvalue="packaging" />
+            <item index="54" class="java.lang.String" itemvalue="pandas" />
+            <item index="55" class="java.lang.String" itemvalue="tqdm" />
+            <item index="56" class="java.lang.String" itemvalue="WTForms" />
+            <item index="57" class="java.lang.String" itemvalue="thinc" />
+            <item index="58" class="java.lang.String" itemvalue="pytz" />
+            <item index="59" class="java.lang.String" itemvalue="transformers" />
+            <item index="60" class="java.lang.String" itemvalue="tensorflow" />
+            <item index="61" class="java.lang.String" itemvalue="sentencepiece" />
+            <item index="62" class="java.lang.String" itemvalue="torch" />
+            <item index="63" class="java.lang.String" itemvalue="beautifulsoup4" />
+            <item index="64" class="java.lang.String" itemvalue="protobuf" />
+            <item index="65" class="java.lang.String" itemvalue="bs4" />
+            <item index="66" class="java.lang.String" itemvalue="dnspython" />
+            <item index="67" class="java.lang.String" itemvalue="sacremoses" />
+            <item index="68" class="java.lang.String" itemvalue="huggingface-hub" />
+            <item index="69" class="java.lang.String" itemvalue="click" />
+            <item index="70" class="java.lang.String" itemvalue="chardet" />
+            <item index="71" class="java.lang.String" itemvalue="langchain" />
+            <item index="72" class="java.lang.String" itemvalue="pyparsing" />
+            <item index="73" class="java.lang.String" itemvalue="llama-index" />
+            <item index="74" class="java.lang.String" itemvalue="Flask" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8Inspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="E501" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N802" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="main.loa_and_contract" />
+          <option value="Backend.API.pdfwriter.addCrypto.*" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (translations)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/translations.iml" filepath="$PROJECT_DIR$/.idea/translations.iml" />
+    </modules>
+  </component>
+</project>

.idea/translations.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.9 (translations)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import MarianMTModel, MarianTokenizer
+
+
+def gradio_input(txt):
+    translated = translate(txt)
+    return translated[0]
+
+
+def translate(text):
+    hub_repo_name = 'dataequity/dataequity-kde4-en-es-qlora'
+    tokenizer = MarianTokenizer.from_pretrained(hub_repo_name)
+    finetuned_model = MarianMTModel.from_pretrained(hub_repo_name)
+
+    try:
+        translated = finetuned_model.generate(**tokenizer([text], return_tensors="pt", padding=True))
+        return [tokenizer.decode(t, skip_special_tokens=True) for t in translated]
+    except:
+        return ['Invalid input']
+
+
+iface = gr.Interface(fn=gradio_input,
+                     inputs=gr.Textbox(placeholder="English text"),
+                     outputs=gr.Textbox(placeholder="Translation"),
+                     title="Translate English to Spanish")
+iface.launch()

requirements.txt

@@ -0,0 +1,10 @@
+gradio
+torch==2.1.2
+numpy==1.26.3
+sacrebleu==2.4.0
+sacremoses==0.1.1
+safetensors==0.4.1
+sentencepiece==0.1.99
+tokenizers==0.15.0
+transformers==4.36.2
+