initial commit

.gitignore

@@ -0,0 +1,162 @@
+# 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-project.org/#use-with-ide
+.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/

README.md

@@ -0,0 +1,15 @@
+# decent-whisper
+
+use the fastest whisper implementation on every hardware
+
+```diff
+- this package is highly work-in-progress and not ready for usage yet
+```
+
+## backends
+
+Currently, this package can dispatch to (in order of preference):
+
+1. [insanely-fast-whisper](https://github.com/Vaibhavs10/insanely-fast-whisper)
+2. [lightning-whisper-mlx](https://github.com/mustafaaljadery/lightning-whisper-mlx)
+3. [faster-whisper](https://github.com/SYSTRAN/faster-whisper)

pyproject.toml

@@ -0,0 +1,25 @@
+[project]
+name = "decent-whisper"
+version = "0.1.0"
+description = "use the fastest whisper implementation on every hardware"
+authors = [{ name = "Jaro Habiger", email = "[email protected]" }]
+dependencies = ["faster-whisper>=1.0.1", "torch>=2.3.0"]
+requires-python = ">= 3.10"
+readme = "README.md"
+license = { text = "AGPL-3.0" }
+
+[project.optional-dependencies]
+macOS = ["lightning-whisper-mlx>=0.0.10", "mlx>=0.12.0"]
+cuda = [
+    "insanely-fast-whisper>=0.0.8",
+    "flash-attn>=2.5.8",
+    "transformers>=4.39.3",
+]
+
+[build-system]
+requires = ["pdm-backend"]
+build-backend = "pdm.backend"
+
+
+[tool.pdm]
+distribution = true

src/decent_whisper/__init__.py

@@ -0,0 +1,9 @@
+from .backends import insanely_fast_whisper, lightning_whisper_mlx, faster_whisper
+
+def get_backend() -> str:
+    if insanely_fast_whisper.should_use():
+        return "insanely-fast-whisper"
+    elif lightning_whisper_mlx.should_use():
+        return "lightning-whisper-mlx"
+    else:
+        return "faster-whisper"

src/decent_whisper/backends/faster_whisper.py

@@ -0,0 +1,4 @@
+#import faster_whisper
+#import faster_whisper.transcribe
+#from faster_whisper import WhisperModel
+

src/decent_whisper/backends/insanely_fast_whisper.py

@@ -0,0 +1,29 @@
+import torch
+#from transformers import pipeline
+#from transformers.utils import is_flash_attn_2_available
+
+def should_use():
+    return torch.cuda.is_available()
+
+def load_model():
+    pass
+
+def transcribe():
+
+
+    pipe = pipeline(
+        "automatic-speech-recognition",
+        model="openai/whisper-large-v3", # select checkpoint from https://huggingface.co/openai/whisper-large-v3#model-details
+        torch_dtype=torch.float16,
+        device="cuda:0", # or mps for Mac devices
+        model_kwargs={"attn_implementation": "flash_attention_2"} if is_flash_attn_2_available() else {"attn_implementation": "sdpa"},
+    )
+
+    outputs = pipe(
+        "<FILE_NAME>",
+        chunk_length_s=30,
+        batch_size=24,
+        return_timestamps=True,
+    )
+
+    outputs

src/decent_whisper/backends/lightning_whisper_mlx.py

@@ -0,0 +1,15 @@
+#from lightning_whisper_mlx import LightningWhisperMLX
+
+def should_use():
+    try:
+        import mlx
+        return True
+    except ImportError:
+        return False
+
+def transcribe():
+    whisper = LightningWhisperMLX(model="distil-medium.en", batch_size=12, quant=None)
+
+    text = whisper.transcribe(audio_path="/audio.mp3")['text']
+
+    print(text)