initial commit

.gitignore

@@ -0,0 +1,231 @@
+/output
+/public
+
+# Created by https://www.toptal.com/developers/gitignore/api/-f,python,linux,vim,quarto,markdown,jupyternotebooks
+# Edit at https://www.toptal.com/developers/gitignore?templates=-f,python,linux,vim,quarto,markdown,jupyternotebooks
+
+#!! ERROR: -f is undefined. Use list command to see defined gitignore types !!#
+
+### JupyterNotebooks ###
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+#!! ERROR: markdown is undefined. Use list command to see defined gitignore types !!#
+
+### Python ###
+# 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
+
+# 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
+
+# IPython
+
+# 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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+#!! ERROR: quarto is undefined. Use list command to see defined gitignore types !!#
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+!*.svg  # comment out if you don't need vector files
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+# End of https://www.toptal.com/developers/gitignore/api/-f,python,linux,vim,quarto,markdown,jupyternotebooks

nlp_interview_transcription/model.py

@@ -0,0 +1,18 @@
+# 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
+
+# set up locale
+import locale
+locale.getpreferredencoding = lambda: "UTF-8"
+
+# prepend silent audio to clip
+from pydub import AudioSegment
+
+spacermilli = 2000
+spacer = AudioSegment.silent(duration=spacermilli)
+
+
+audio = AudioSegment.from_wav("input.wav") 
+
+audio = spacer.append(audio, crossfade=0)
+
+audio.export('input_prep.wav', format='wav')

nlp_interview_transcription/notebook.py

@@ -0,0 +1,24 @@
+## SETTINGS FOR LATER
+from pathlib import Path
+
+# @markdown Enter the URL of the YouTube video, or the path to the video/audio file you want to transcribe, give the output path, etc. and run the cell. HTML file embeds the video for YouTube, and audio for media files.
+
+Source = "Youtube"  # @param ['Youtube', 'File (Google Drive)']
+# @markdown ---
+# @markdown #### **Youtube video**
+video_url = "https://youtu.be/hpZFJctBUHQ"  # @param {type:"string"}
+# store_audio = True #@param {type:"boolean"}
+# @markdown ---
+# @markdown #### **Google Drive video or audio path (mp4, wav, mp3)**
+video_path = "/content/drive/MyDrive/Customer_Service.mp3"  # @param {type:"string"}
+# @markdown ---
+output_path = "/content/transcript/"  # @param {type:"string"}
+output_path = str(Path(output_path))
+# @markdown ---
+# @markdown #### **Title for transcription of media file**
+audio_title = "Sample Order Taking"  # @param {type:"string"}
+# @markdown ---
+# @markdown #### Copy a token from your [Hugging Face tokens page](https://huggingface.co/settings/tokens) and paste it below.
+access_token = "hf_"  # @param {type:"string"}
+# @markdown ---
+# @markdown **Run this cell again if you change the video.**

pyproject.toml

@@ -0,0 +1,15 @@
+[tool.poetry]
+name = "nlp-interview-transcription"
+version = "0.1.0"
+description = ""
+authors = ["Marty Oehme <marty.oehme@gmail.com>"]
+readme = "README.md"
+packages = [{include = "src"}]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"