Merge pull request #13 from CLARIN-PL/change_data_model

Change data model

.dockerignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# IDE settings
+.vscode/
+
+# macOS
+.DS_Store
+
+debug_run/
+publish_to_theliver.sh
+
+.idea
+
+experiment_data
+cache_asr_scripts
+
+docker/embedding_models/
+docker/wav2vec2for_ctc_models/
+.dvc
+
+*.bin
+*.gz

.dvc/.gitignore

+/config.local
+/tmp
+/cache

.dvc/config

+[core]
+    remote = clarin-biz-asr-benchmarks
+    autostage = true
+    hardlink_lock = true
+['remote "clarin-biz-asr-benchmarks"']
+    url = s3://projects/clarin-biz-asr-benchmark/dvc
+    endpointurl = https://s3.clarin-pl.eu

.dvc/plots/confusion.json

+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "facet": {
+        "field": "rev",
+        "type": "nominal"
+    },
+    "spec": {
+        "transform": [
+            {
+                "aggregate": [
+                    {
+                        "op": "count",
+                        "as": "xy_count"
+                    }
+                ],
+                "groupby": [
+                    "<DVC_METRIC_Y>",
+                    "<DVC_METRIC_X>"
+                ]
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_Y>"
+                ],
+                "key": "<DVC_METRIC_X>",
+                "value": 0
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_X>"
+                ],
+                "key": "<DVC_METRIC_Y>",
+                "value": 0
+            },
+            {
+                "joinaggregate": [
+                    {
+                        "op": "max",
+                        "field": "xy_count",
+                        "as": "max_count"
+                    }
+                ],
+                "groupby": []
+            },
+            {
+                "calculate": "datum.xy_count / datum.max_count",
+                "as": "percent_of_max"
+            }
+        ],
+        "encoding": {
+            "x": {
+                "field": "<DVC_METRIC_X>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_X_LABEL>"
+            },
+            "y": {
+                "field": "<DVC_METRIC_Y>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_Y_LABEL>"
+            }
+        },
+        "layer": [
+            {
+                "mark": "rect",
+                "width": 300,
+                "height": 300,
+                "encoding": {
+                    "color": {
+                        "field": "xy_count",
+                        "type": "quantitative",
+                        "title": "",
+                        "scale": {
+                            "domainMin": 0,
+                            "nice": true
+                        }
+                    }
+                }
+            },
+            {
+                "mark": "text",
+                "encoding": {
+                    "text": {
+                        "field": "xy_count",
+                        "type": "quantitative"
+                    },
+                    "color": {
+                        "condition": {
+                            "test": "datum.percent_of_max > 0.5",
+                            "value": "white"
+                        },
+                        "value": "black"
+                    }
+                }
+            }
+        ]
+    }
+}

.dvc/plots/confusion_normalized.json

+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "facet": {
+        "field": "rev",
+        "type": "nominal"
+    },
+    "spec": {
+        "transform": [
+            {
+                "aggregate": [
+                    {
+                        "op": "count",
+                        "as": "xy_count"
+                    }
+                ],
+                "groupby": [
+                    "<DVC_METRIC_Y>",
+                    "<DVC_METRIC_X>"
+                ]
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_Y>"
+                ],
+                "key": "<DVC_METRIC_X>",
+                "value": 0
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_X>"
+                ],
+                "key": "<DVC_METRIC_Y>",
+                "value": 0
+            },
+            {
+                "joinaggregate": [
+                    {
+                        "op": "sum",
+                        "field": "xy_count",
+                        "as": "sum_y"
+                    }
+                ],
+                "groupby": [
+                    "<DVC_METRIC_Y>"
+                ]
+            },
+            {
+                "calculate": "datum.xy_count / datum.sum_y",
+                "as": "percent_of_y"
+            }
+        ],
+        "encoding": {
+            "x": {
+                "field": "<DVC_METRIC_X>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_X_LABEL>"
+            },
+            "y": {
+                "field": "<DVC_METRIC_Y>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_Y_LABEL>"
+            }
+        },
+        "layer": [
+            {
+                "mark": "rect",
+                "width": 300,
+                "height": 300,
+                "encoding": {
+                    "color": {
+                        "field": "percent_of_y",
+                        "type": "quantitative",
+                        "title": "",
+                        "scale": {
+                            "domain": [
+                                0,
+                                1
+                            ]
+                        }
+                    }
+                }
+            },
+            {
+                "mark": "text",
+                "encoding": {
+                    "text": {
+                        "field": "percent_of_y",
+                        "type": "quantitative",
+                        "format": ".2f"
+                    },
+                    "color": {
+                        "condition": {
+                            "test": "datum.percent_of_y > 0.5",
+                            "value": "white"
+                        },
+                        "value": "black"
+                    }
+                }
+            }
+        ]
+    }
+}

.dvc/plots/linear.json

+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "width": 300,
+    "height": 300,
+    "layer": [
+        {
+            "encoding": {
+                "x": {
+                    "field": "<DVC_METRIC_X>",
+                    "type": "quantitative",
+                    "title": "<DVC_METRIC_X_LABEL>"
+                },
+                "y": {
+                    "field": "<DVC_METRIC_Y>",
+                    "type": "quantitative",
+                    "title": "<DVC_METRIC_Y_LABEL>",
+                    "scale": {
+                        "zero": false
+                    }
+                },
+                "color": {
+                    "field": "rev",
+                    "type": "nominal"
+                }
+            },
+            "layer": [
+                {
+                    "mark": "line"
+                },
+                {
+                    "selection": {
+                        "label": {
+                            "type": "single",
+                            "nearest": true,
+                            "on": "mouseover",
+                            "encodings": [
+                                "x"
+                            ],
+                            "empty": "none",
+                            "clear": "mouseout"
+                        }
+                    },
+                    "mark": "point",
+                    "encoding": {
+                        "opacity": {
+                            "condition": {
+                                "selection": "label",
+                                "value": 1
+                            },
+                            "value": 0
+                        }
+                    }
+                }
+            ]
+        },
+        {
+            "transform": [
+                {
+                    "filter": {
+                        "selection": "label"
+                    }
+                }
+            ],
+            "layer": [
+                {
+                    "mark": {
+                        "type": "rule",
+                        "color": "gray"
+                    },
+                    "encoding": {
+                        "x": {
+                            "field": "<DVC_METRIC_X>",
+                            "type": "quantitative"
+                        }
+                    }
+                },
+                {
+                    "encoding": {
+                        "text": {
+                            "type": "quantitative",
+                            "field": "<DVC_METRIC_Y>"
+                        },
+                        "x": {
+                            "field": "<DVC_METRIC_X>",
+                            "type": "quantitative"
+                        },
+                        "y": {
+                            "field": "<DVC_METRIC_Y>",
+                            "type": "quantitative"
+                        }
+                    },
+                    "layer": [
+                        {
+                            "mark": {
+                                "type": "text",
+                                "align": "left",
+                                "dx": 5,
+                                "dy": -5
+                            },
+                            "encoding": {
+                                "color": {
+                                    "type": "nominal",
+                                    "field": "rev"
+                                }
+                            }
+                        }
+                    ]
+                }
+            ]
+        }
+    ]
+}

.dvc/plots/scatter.json

+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "width": 300,
+    "height": 300,
+    "layer": [
+        {
+            "encoding": {
+                "x": {
+                    "field": "<DVC_METRIC_X>",
+                    "type": "quantitative",
+                    "title": "<DVC_METRIC_X_LABEL>"
+                },
+                "y": {
+                    "field": "<DVC_METRIC_Y>",
+                    "type": "quantitative",
+                    "title": "<DVC_METRIC_Y_LABEL>",
+                    "scale": {
+                        "zero": false
+                    }
+                },
+                "color": {
+                    "field": "rev",
+                    "type": "nominal"
+                }
+            },
+            "layer": [
+                {
+                    "mark": "point"
+                },
+                {
+                    "selection": {
+                        "label": {
+                            "type": "single",
+                            "nearest": true,
+                            "on": "mouseover",
+                            "encodings": [
+                                "x"
+                            ],
+                            "empty": "none",
+                            "clear": "mouseout"
+                        }
+                    },
+                    "mark": "point",
+                    "encoding": {
+                        "opacity": {
+                            "condition": {
+                                "selection": "label",
+                                "value": 1
+                            },
+                            "value": 0
+                        }
+                    }
+                }
+            ]
+        },
+        {
+            "transform": [
+                {
+                    "filter": {
+                        "selection": "label"
+                    }
+                }
+            ],
+            "layer": [
+                {
+                    "encoding": {
+                        "text": {
+                            "type": "quantitative",
+                            "field": "<DVC_METRIC_Y>"
+                        },
+                        "x": {
+                            "field": "<DVC_METRIC_X>",
+                            "type": "quantitative"
+                        },
+                        "y": {
+                            "field": "<DVC_METRIC_Y>",
+                            "type": "quantitative"
+                        }
+                    },
+                    "layer": [
+                        {
+                            "mark": {
+                                "type": "text",
+                                "align": "left",
+                                "dx": 5,
+                                "dy": -5
+                            },
+                            "encoding": {
+                                "color": {
+                                    "type": "nominal",
+                                    "field": "rev"
+                                }
+                            }
+                        }
+                    ]
+                }
+            ]
+        }
+    ]
+}

.dvc/plots/simple.json

+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "width": 300,
+    "height": 300,
+    "mark": {
+        "type": "line"
+    },
+    "encoding": {
+        "x": {
+            "field": "<DVC_METRIC_X>",
+            "type": "quantitative",
+            "title": "<DVC_METRIC_X_LABEL>"
+        },
+        "y": {
+            "field": "<DVC_METRIC_Y>",
+            "type": "quantitative",
+            "title": "<DVC_METRIC_Y_LABEL>",
+            "scale": {
+                "zero": false
+            }
+        },
+        "color": {
+            "field": "rev",
+            "type": "nominal"
+        }
+    }
+}

.dvc/plots/smooth.json

+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "mark": {
+        "type": "line"
+    },
+    "encoding": {
+        "x": {
+            "field": "<DVC_METRIC_X>",
+            "type": "quantitative",
+            "title": "<DVC_METRIC_X_LABEL>"
+        },
+        "y": {
+            "field": "<DVC_METRIC_Y>",
+            "type": "quantitative",
+            "title": "<DVC_METRIC_Y_LABEL>",
+            "scale": {
+                "zero": false
+            }
+        },
+        "color": {
+            "field": "rev",
+            "type": "nominal"
+        }
+    },
+    "transform": [
+        {
+            "loess": "<DVC_METRIC_Y>",
+            "on": "<DVC_METRIC_X>",
+            "groupby": [
+                "rev"
+            ],
+            "bandwidth": 0.3
+        }
+    ]
+}

.dvcignore

+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.github/workflows/python-package.yml

-name: CI
-on: pull_request
-
-jobs:
-    tests:
-        strategy:
-            fail-fast: false
-            matrix:
-                python-version: [ 3.9.6 ]
-                poetry-version: [ 1.1.5 ]
-                # os: [ ubuntu-20.04, macos-latest, windows-latest ]
-                os: [ ubuntu-20.04 ]
-        runs-on: ${{ matrix.os }}
-        steps:
-            -   uses: actions/checkout@v2
-            -   uses: actions/setup-python@v2
-                with:
-                    python-version: ${{ matrix.python-version }}
-            -   name: Install poetry
-                uses: abatilo/actions-poetry@v2.0.0
-                with:
-                    poetry-version: ${{ matrix.poetry-version }}
-            -   name: Install deps
-                run: poetry install -vv
-            -   name: Run tests
-                run: poetry run poe test
-    lint:
-        strategy:
-            fail-fast: false
-            matrix:
-                python-version: [ 3.9.6 ]
-                poetry-version: [ 1.1.5 ]
-                os: [ ubuntu-20.04 ]
-        runs-on: ${{ matrix.os }}
-        steps:
-            -   uses: actions/checkout@v2
-            -   uses: actions/setup-python@v2
-                with:
-                    python-version: ${{ matrix.python-version }}
-            -   name: Install poetry
-                uses: abatilo/actions-poetry@v2.0.0
-                with:
-                    poetry-version: ${{ matrix.poetry-version }}
-            -   name: Install deps
-                run: poetry install -vv
-            -   name: Check
-                run: poetry run poe check
-    publish:
-        needs:
-            - tests
-            - lint
-        environment: Test deployment
-        strategy:
-            fail-fast: false
-            matrix:
-                python-version: [ 3.9.6 ]
-                poetry-version: [ 1.1.5 ]
-                os: [ ubuntu-20.04 ]
-        runs-on: ${{ matrix.os }}
-        steps:
-            -   uses: actions/checkout@v2
-                with:
-                    fetch-depth: 0
-            -   uses: actions/setup-python@v2
-                with:
-                    python-version: ${{ matrix.python-version }}
-            -   name: Install poetry
-                uses: abatilo/actions-poetry@v2.0.0
-                with:
-                    poetry-version: ${{ matrix.poetry-version }}
-            -   name: Install deps
-                run: poetry install -vv
-            -   name: Build and publish
-                run: |
-                    poetry version "$(poetry version --short)-alpha.${GITHUB_RUN_NUMBER}"
-                    poetry build
-                    poetry config repositories.clarinpypi https://pypi.clarin-pl.eu/
-                    poetry publish -r clarinpypi --username ${{ secrets.PYPI_USER }} --password ${{ secrets.PYPI_PASS }}
+#name: CI
+#on: pull_request
+#
+#jobs:
+#    tests:
+#        strategy:
+#            fail-fast: false
+#            matrix:
+#                python-version: [ 3.9.6 ]
+#                poetry-version: [ 1.1.5 ]
+#                # os: [ ubuntu-20.04, macos-latest, windows-latest ]
+#                os: [ ubuntu-20.04 ]
+#        runs-on: ${{ matrix.os }}
+#        steps:
+#            -   uses: actions/checkout@v2
+#            -   uses: actions/setup-python@v2
+#                with:
+#                    python-version: ${{ matrix.python-version }}
+#            -   name: Install poetry
+#                uses: abatilo/actions-poetry@v2.0.0
+#                with:
+#                    poetry-version: ${{ matrix.poetry-version }}
+#            -   name: Install deps
+#                run: poetry install -vv
+#            -   name: Run tests
+#                run: poetry run poe test
+#    lint:
+#        strategy:
+#            fail-fast: false
+#            matrix:
+#                python-version: [ 3.9.6 ]
+#                poetry-version: [ 1.1.5 ]
+#                os: [ ubuntu-20.04 ]
+#        runs-on: ${{ matrix.os }}
+#        steps:
+#            -   uses: actions/checkout@v2
+#            -   uses: actions/setup-python@v2
+#                with:
+#                    python-version: ${{ matrix.python-version }}
+#            -   name: Install poetry
+#                uses: abatilo/actions-poetry@v2.0.0
+#                with:
+#                    poetry-version: ${{ matrix.poetry-version }}
+#            -   name: Install deps
+#                run: poetry install -vv
+#            -   name: Check
+#                run: poetry run poe check
+#    publish:
+#        needs:
+#            - tests
+#            - lint
+#        environment: Test deployment
+#        strategy:
+#            fail-fast: false
+#            matrix:
+#                python-version: [ 3.9.6 ]
+#                poetry-version: [ 1.1.5 ]
+#                os: [ ubuntu-20.04 ]
+#        runs-on: ${{ matrix.os }}
+#        steps:
+#            -   uses: actions/checkout@v2
+#                with:
+#                    fetch-depth: 0
+#            -   uses: actions/setup-python@v2
+#                with:
+#                    python-version: ${{ matrix.python-version }}
+#            -   name: Install poetry
+#                uses: abatilo/actions-poetry@v2.0.0
+#                with:
+#                    poetry-version: ${{ matrix.poetry-version }}
+#            -   name: Install deps
+#                run: poetry install -vv
+#            -   name: Build and publish
+#                run: |
+#                    poetry version "$(poetry version --short)-alpha.${GITHUB_RUN_NUMBER}"
+#                    poetry build
+#                    poetry config repositories.clarinpypi https://pypi.clarin-pl.eu/
+#                    poetry publish -r clarinpypi --username ${{ secrets.PYPI_USER }} --password ${{ secrets.PYPI_PASS }}

.gitignore

 # Byte-compiled / optimized / DLL files
 __pycache__/
+**/__pycache__/
 *.py[cod]
 *$py.class
 
@@ -109,3 +110,8 @@ ENV/
 
 debug_run/
 publish_to_theliver.sh
+
+.idea
+
+docker/embedding_models/
+docker/wav2vec2for_ctc_models/

.idea/.gitignore

-# Default ignored files
-/shelf/
-/workspace.xml
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml
-# Editor-based HTTP Client requests
-/httpRequests/

.idea/asr-benchmarks.iml

-<?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="inheritedJdk" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-  <component name="PyDocumentationSettings">
-    <option name="format" value="PLAIN" />
-    <option name="myDocStringFormat" value="Plain" />
-  </component>
-  <component name="TestRunnerService">
-    <option name="PROJECT_TEST_RUNNER" value="pytest" />
-  </component>
-</module>
\ No newline at end of file

.idea/codeStyles/codeStyleConfig.xml

-<component name="ProjectCodeStyleConfiguration">
-  <state>
-    <option name="PREFERRED_PROJECT_CODE_STYLE" value="Default" />
-  </state>
-</component>
\ No newline at end of file

.idea/inspectionProfiles/Project_Default.xml

-<component name="InspectionProjectProfileManager">
-  <profile version="1.0">
-    <option name="myName" value="Project Default" />
-    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
-    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
-      <option name="ignoredPackages">
-        <value>
-          <list size="6">
-            <item index="0" class="java.lang.String" itemvalue="tensorflow-gpu" />
-            <item index="1" class="java.lang.String" itemvalue="tensorflow" />
-            <item index="2" class="java.lang.String" itemvalue="mysql-connector-python" />
-            <item index="3" class="java.lang.String" itemvalue="dateutil" />
-            <item index="4" class="java.lang.String" itemvalue="pytest" />
-            <item index="5" class="java.lang.String" itemvalue="celery" />
-          </list>
-        </value>
-      </option>
-    </inspection_tool>
-    <inspection_tool class="PyPep8Inspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
-      <option name="ignoredErrors">
-        <list>
-          <option value="E402" />
-        </list>
-      </option>
-    </inspection_tool>
-    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
-      <option name="ignoredIdentifiers">
-        <list>
-          <option value="dict.__getitem__" />
-        </list>
-      </option>
-    </inspection_tool>
-  </profile>
-</component>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>
\ No newline at end of file

.idea/misc.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (asr-benchmarks)" project-jdk-type="Python SDK" />
-</project>
\ No newline at end of file

.idea/modules.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/asr-benchmarks.iml" filepath="$PROJECT_DIR$/.idea/asr-benchmarks.iml" />
-    </modules>
-  </component>
-</project>
\ No newline at end of file

.idea/mypy.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="MypyConfigService">
-    <option name="customMypyPath" value="$USER_HOME$/miniconda3/envs/asr-benchmarks/bin/mypy" />
-  </component>
-</project>
\ No newline at end of file