Add pre-commit, poetry and use type hinting

.pre-commit-config.yaml

@@ -0,0 +1,28 @@
+default_language_version:
+  python: python3.11
+
+repos:
+  # mypy checks type annotations.
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.0
+    hooks:
+      - id: mypy
+        args: [--config-file=pyproject.toml]
+
+  # pre-commit-hooks is a collection of Git hooks for code quality, formatting, and analysis.
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
+      - id: check-toml
+      - id: debug-statements
+
+  # An extremely fast Python linter and code formatter, written in Rust.
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.4.5
+    hooks:
+    -   id: ruff
+        args:
+        - --fix
+    -   id: ruff-format

README.md

@@ -1,4 +1,5 @@
 # Whisper Mic
+
 This repo is based on the work done [here](https://github.com/openai/whisper) by OpenAI.  This repo allows you use use a mic as demo. This repo copies some of the README from the original project.
 
 ## Video Tutorial
@@ -20,8 +21,7 @@ Now a pip package!
 
 ## Available models and languages
 
-There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs. Below are the names of the available models and their approximate memory requirements and relative speed. 
-
+There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs. Below are the names of the available models and their approximate memory requirements and relative speed.
 
 |  Size  | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed |
 |:------:|:----------:|:------------------:|:------------------:|:-------------:|:--------------:|
@@ -35,13 +35,15 @@ For English-only applications, the `.en` models tend to perform better, especial
 
 ## Microphone Demo
 
-You can use the model with a microphone using the ```whisper_mic``` program.  Use ```-h``` to see flag options.
+You can use the model with a microphone using the ```whisper_mic``` program.  Use ```--help``` to see flag options.
+
+> Example: ```python -m whisper_mic --help```
 
 Some of the more important flags are the ```--model``` and ```--english``` flags.
 
 ## Transcribing To A File
 
-Using the command: ```whisper_mic --loop --dictate``` will type the words you say on your active cursor.
+Using the command: ```python -m whisper_mic --loop --dictate``` will type the words you say on your active cursor.
 
 ## Usage In Other Projects
 
@@ -60,22 +62,27 @@ Check out what the possible arguments are by looking at the ```cli.py``` file
 ## Troubleshooting
 
 If you are having issues, try the following:
-```
+
+```bash
 sudo apt install portaudio19-dev python3-pyaudio
 ```
 
 ## Contributing
 
 Some ideas that you can add are:
+
 1. Supporting different implementations of Whisper
 2. Adding additional optional functionality.
 3. Add tests
 
+Be sure to run ```pre-commit install``` before making any changes and running it before committing with ```pre-commit run --all-files```.
+
 ## License
 
 The model weights of Whisper are released under the MIT License. See their repo for more information.
 
 This code under this repo is under the MIT license.  See [LICENSE](LICENSE) for further details.
 
 ## Thanks
+
 Until recently, access to high performing speech to text models was only available through paid serviecs.  With this release, I am excited for the many applications that will come.

pyproject.toml

@@ -1,40 +1,139 @@
-[build-system]
-requires = ["setuptools>=61.0"]
-build-backend = "setuptools.build_meta"
-
-[project]
+[tool.poetry]
 name = "whisper_mic"
 version = "1.4.2"
 authors = [
-  { name="Blake Mallory", email="blakecmallory@gmail.com" },
+  "Blake Mallory <blakecmallory@gmail.com>",
 ]
 description = "Whisper for your microphone"
 readme = "README.md"
-requires-python = ">=3.9"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
 ]
-dependencies = [
-    'importlib-metadata; python_version>"3.9"',
-    "attrs",
-    "click",
-    "ffmpeg-python",
-    "more-itertools",
-    "numpy",
-    "openai-whisper",
-    "pyaudio",
-    "pydantic",
-    "pydub",
-    "pynput",
-    "requests",
-    "rich",
-    "speechrecognition",
-    "tdqm",
-    "torch",
-    "transformers",
-]
 
-[project.scripts]
+[tool.poetry.dependencies]
+python = "^3.11.0"
+
+click = "^8.1.7"
+ffmpeg-python= "0.2.0"
+more-itertools = "^10.2.0"
+numpy = "^1.26.4"
+openai-whisper = "^20231117"
+pyaudio = "^0.2.14"
+pydub = "^0.25.1"
+pynput = "^1.7.6"
+rich = "^13.7.1"
+speechrecognition = "^3.10.4"
+tqdm = "^4.66.4"
+torch = "^2.3.0"
+transformers = "^4.40.2"
+
+[tool.poetry.group.dev.dependencies]
+mypy = "1.10.0"
+pre-commit = "3.7.1"
+pre-commit-hooks = "4.6.0"
+ruff = "0.4.5"
+
+[tool.poetry.scripts]
 whisper_mic = "whisper_mic.cli:main"
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.mypy]
+python_version = "3.11"
+
+check_untyped_defs = true
+disallow_untyped_defs = true
+incremental = false
+ignore_errors = false
+pretty = true
+show_error_context = true
+show_traceback = true
+strict_optional = true
+warn_incomplete_stub = true
+warn_no_return = true
+warn_redundant_casts = true
+warn_return_any = true
+warn_unreachable = true
+warn_unused_configs = true
+warn_unused_ignores = true
+
+[[tool.mypy.overrides]]
+module = [
+    "click.*",
+    "faster_whisper.*",
+    "numpy.*",
+    "pynput.*",
+    "rich.*",
+    "speech_recognition.*",
+    "torch.*",
+    "whisper.*",
+]
+ignore_missing_imports = true
+
+[tool.ruff]
+target-version = "py311"
+
+exclude = ["alembic"]
+indent-width = 4
+line-length = 110
+
+[tool.ruff.lint]
+# rules from: https://docs.astral.sh/ruff/rules/
+select = [
+    "ANN",  # flake8-annotations
+    "ASYNC",  # flake8-async
+    "S",  # flake8-bandit
+    "B",  # flake8-bugbear
+    "A",  # flake8-builtins
+    "COM",  # flake8-commas
+    "C4",  # flake8-comprehensions
+    "DTZ",  # flake8-datetimez
+    "EM",  # flake8-errmsg
+    "LOG",  # flake8-logging
+    "G",  # flake8-logging-format
+    "PIE",  # flake8-pie
+    "T20",  # flake8-print
+    "PT",  # flake8-pytest-style
+    "Q",  # flake8-quotes
+    "RSE",  # flake8-raise
+    "RET",  # flake8-return
+    "SIM",  # flake8-simplify
+    "TID",  # flake8-tidy-imports
+    "ARG",  # flake8-unused-arguments
+    "I",  # isort
+    "N",  # pep8-naming
+    "E",  # pycodestyle errors
+    "W",  # pycodestyle warnings
+    "F",  # pyflakes
+    "UP",  # pyupgrade
+    "RUF",  # Ruff-specific rules
+    "TRY",  # tryceratops
+]
+ignore = [
+    "ANN101",  # Missing type annotation for `self` in method
+    "B008",  # Do not perform function calls in argument defaults
+    "E501",  # Line too long, handled by black
+    "G004",  # Logging statements should not use f"..."
+    "W191",  # Indentation contains tabs
+]
+fixable = ["ALL"]
+unfixable = []
+# logger-objects = ["logging_setup.logger"]  # TODO: test first
+
+[tool.ruff.format]
+line-ending = "auto"
+quote-style = "double"
+skip-magic-trailing-comma = false
+
+[tool.ruff.lint.isort]
+# force-sort-within-sections = true  # TODO: test first
+lines-after-imports = 2
+lines-between-types = 1
+
+[tool.ruff.lint.pyupgrade]
+# Preserve types, even if a file imports `from __future__ import annotations`.
+keep-runtime-typing = true

whisper_mic/__init__.py

@@ -1,2 +0,0 @@
-from .whisper_mic import *
-from .utils import *

whisper_mic/__main__.py

@@ -0,0 +1,5 @@
+from whisper_mic.cli import main
+
+
+if __name__ == "__main__":
+    main()