Initial commit

.gitignore

@@ -0,0 +1,164 @@
+### 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
+
+# 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
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/audio-transcript.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 3.10 (audio-transcript)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.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 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.10 (audio-transcript)" />
+  </component>
+</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/audio-transcript.iml" filepath="$PROJECT_DIR$/.idea/audio-transcript.iml" />
+    </modules>
+  </component>
+</project>

.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>

README.md

@@ -0,0 +1,74 @@
+# Project README
+
+## Setting Up the Project Environment
+
+Follow the steps below to set up your project environment:
+
+### 1. Create a Virtual Environment
+
+To isolate the project dependencies and prevent conflicts, create a virtual environment using the following commands:
+
+```bash
+# Create the virtual environment
+python3 -m venv venv
+
+# Activate the virtual environment:
+source venv/bin/activate
+```
+
+### 2. Install Project Dependencies
+
+Once the virtual environment is activated, install the required dependencies using `pip`:
+
+```bash
+pip install -r requirements.txt
+```
+
+Make sure you have a `requirements.txt` file in the project directory with the list of all required dependencies.
+
+## Running the Script
+
+To run the Python script `transcribe.py`, you need to provide an audio file as a parameter. Use the following command:
+
+```bash
+python transcribe.py <audio_file>
+```
+
+- Replace `<audio_file>` with the path to your audio file.
+- Example:
+
+```bash
+python transcribe.py sample_audio.wav
+```
+
+## Where is downloaded the AI Whisper model ?
+
+When using the `openai-whisper` package, the AI Whisper model is downloaded and stored in a local cache directory. By
+default, it is stored under the user's home directory in the following path:
+
+```plaintext
+~/.cache/whisper/
+```
+
+Here:
+
+- `~` refers to the user's home directory.
+- `.cache/whisper/` is the folder where the models are cached.
+
+The cache directory contains the downloaded model files, which are reused in subsequent runs to avoid re-downloading
+them. Specifically:
+
+- Whisper downloads the model files when they are first used, based on the requested model size (e.g., `base`, `medium`,
+  or `large`).
+
+If you need to modify or relocate the cache directory, you can set the `WHISPER_CACHE_DIR` environment variable to
+specify a custom path for storing these files.
+
+
+## Notes
+
+- Ensure that your virtual environment is activated before running the script.
+- If you encounter any missing dependencies, double-check your `requirements.txt` file and re-run the installation
+  command.
+
+Happy coding!

requirements.txt

@@ -0,0 +1,2 @@
+openai-whisper==20240930
+torch==2.6.0

transcribe.py

@@ -0,0 +1,23 @@
+import sys
+import whisper
+
+def transcribe_audio(audio_path):
+    # Load the Whisper model
+    model = whisper.load_model("base")
+
+    # Transcribe the audio file
+    print(f"Transcribing: {audio_path} ...")
+    result = model.transcribe(audio_path, language="fr")
+
+    # Print and return transcription
+    transcription = result["text"]
+    print("\nTranscription:\n")
+    print(transcription)
+    return transcription
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python transcribe.py path/to/audiofile")
+    else:
+        audio_file = sys.argv[1]
+        transcribe_audio(audio_file)