chore: bump whisperX to 3.3.0

feat: restrict Python versions to 3.9 - 3.12

.github/workflows/build-and-release.yml

@@ -0,0 +1,35 @@
+name: Build and release
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install build
+
+      - name: Build wheels
+        run: python -m build --wheel
+
+      - name: Release to Github
+        uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+
+      - name: Publish package to PyPi
+        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/python-compatibility.yml

@@ -0,0 +1,32 @@
+name: Python Compatibility Test
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch:  # Allows manual triggering from GitHub UI
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package
+        run: |
+          python -m pip install --upgrade pip
+          pip install .
+
+      - name: Test import
+        run: |
+          python -c "import whisperx; print('Successfully imported whisperx')"

.gitignore

@@ -1,3 +1,171 @@
-whisperx.egg-info/
-**/__pycache__/
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/
+
+# PyPI configuration file
+.pypirc

MANIFEST.in

@@ -1,6 +1,3 @@
 include whisperx/assets/*
-include whisperx/assets/gpt2/*
-include whisperx/assets/multilingual/*
-include whisperx/normalizers/english.json
 include LICENSE
 include requirements.txt

README.md

@@ -23,7 +23,7 @@
 </p>
 
 
-<img width="1216" align="center" alt="whisperx-arch" src="figures/pipeline.png">
+<img width="1216" align="center" alt="whisperx-arch" src="https://raw.githubusercontent.com/m-bain/whisperX/refs/heads/main/figures/pipeline.png">
 
 
 <!-- <p align="left">Whisper-Based Automatic Speech Recognition (ASR) with improved timestamp accuracy + quality via forced phoneme alignment and voice-activity based batching for fast inference.</p> -->
@@ -80,21 +80,40 @@ GPU execution requires the NVIDIA libraries cuBLAS 11.x and cuDNN 8.x to be inst
 
 See other methods [here.](https://pytorch.org/get-started/previous-versions/#v200)
 
-### 3. Install this repo
+### 3. Install WhisperX
 
-`pip install git+https://github.com/m-bain/whisperx.git`
+You have several installation options:
 
-If already installed, update package to most recent commit
+#### Option A: Stable Release (recommended)
+Install the latest stable version from PyPI:
 
-`pip install git+https://github.com/m-bain/whisperx.git --upgrade`
-
-If wishing to modify this package, clone and install in editable mode:
+```bash
+pip install whisperx
 ```
-$ git clone https://github.com/m-bain/whisperX.git
-$ cd whisperX
-$ pip install -e .
+
+#### Option B: Development Version
+Install the latest development version directly from GitHub (may be unstable):
+
+```bash
+pip install git+https://github.com/m-bain/whisperx.git
 ```
 
+If already installed, update to the most recent commit:
+
+```bash
+pip install git+https://github.com/m-bain/whisperx.git --upgrade
+```
+
+#### Option C: Development Mode
+If you wish to modify the package, clone and install in editable mode:
+```bash
+git clone https://github.com/m-bain/whisperX.git
+cd whisperX
+pip install -e .
+```
+
+> **Note**: The development version may contain experimental features and bugs. Use the stable PyPI release for production environments.
+
 You may also need to install ffmpeg, rust etc. Follow openAI instructions here https://github.com/openai/whisper#setup.
 
 ### Speaker Diarization

requirements.txt

@@ -1,7 +1,7 @@
 torch>=2
 torchaudio>=2
-faster-whisper==1.0.0
-ctranslate2==4.4.0
+faster-whisper==1.1.0
+ctranslate2<4.5.0
 transformers
 pandas
 setuptools>=65

setup.py

@@ -1,19 +1,22 @@
 import os
-import platform
 
 import pkg_resources
 from setuptools import find_packages, setup
 
+with open("README.md", "r", encoding="utf-8") as f:
+    long_description = f.read()
+
 setup(
     name="whisperx",
     py_modules=["whisperx"],
-    version="3.2.0",
+    version="3.3.0",
     description="Time-Accurate Automatic Speech Recognition using Whisper.",
-    readme="README.md",
-    python_requires=">=3.8",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    python_requires=">=3.9, <3.13",
     author="Max Bain",
     url="https://github.com/m-bain/whisperx",
-    license="MIT",
+    license="BSD-2-Clause",
     packages=find_packages(exclude=["tests*"]),
     install_requires=[
         str(r)
@@ -21,7 +24,7 @@ setup(
             open(os.path.join(os.path.dirname(__file__), "requirements.txt"))
         )
     ]
-    + [f"pyannote.audio==3.1.1"],
+    + [f"pyannote.audio==3.3.2"],
     entry_points={
         "console_scripts": ["whisperx=whisperx.transcribe:cli"],
     },

whisperx/alignment.py

@@ -85,8 +85,8 @@ def load_align_model(language_code, device, model_name=None, model_dir=None):
         align_dictionary = {c.lower(): i for i, c in enumerate(labels)}
     else:
         try:
-            processor = Wav2Vec2Processor.from_pretrained(model_name)
-            align_model = Wav2Vec2ForCTC.from_pretrained(model_name)
+            processor = Wav2Vec2Processor.from_pretrained(model_name, cache_dir=model_dir)
+            align_model = Wav2Vec2ForCTC.from_pretrained(model_name, cache_dir=model_dir)
         except Exception as e:
             print(e)
             print(f"Error loading model from huggingface, check https://huggingface.co/models for finetuned wav2vec2.0 models")

whisperx/asr.py

@@ -171,7 +171,7 @@ class FasterWhisperPipeline(Pipeline):
         return final_iterator
 
     def transcribe(
-        self, audio: Union[str, np.ndarray], batch_size=None, num_workers=0, language=None, task=None, chunk_size=30, print_progress = False, combined_progress=False
+        self, audio: Union[str, np.ndarray], batch_size=None, num_workers=0, language=None, task=None, chunk_size=30, print_progress = False, combined_progress=False, verbose=False
     ) -> TranscriptionResult:
         if isinstance(audio, str):
             audio = load_audio(audio)
@@ -223,6 +223,8 @@ class FasterWhisperPipeline(Pipeline):
             text = out['text']
             if batch_size in [0, 1, None]:
                 text = text[0]
+            if verbose:
+                print(f"Transcript: [{round(vad_segments[idx]['start'], 3)} --> {round(vad_segments[idx]['end'], 3)}] {text}")
             segments.append(
                 {
                     "text": text,
@@ -267,6 +269,7 @@ def load_model(whisper_arch,
                model : Optional[WhisperModel] = None,
                task="transcribe",
                download_root=None,
+               local_files_only=False,
                threads=4):
     '''Load a Whisper model for inference.
     Args:
@@ -277,6 +280,7 @@ def load_model(whisper_arch,
         language: str - The language of the model. (use English for now)
         model: Optional[WhisperModel] - The WhisperModel instance to use.
         download_root: Optional[str] - The root directory to download the model to.
+        local_files_only: bool - If `True`, avoid downloading the file and return the path to the local cached file if it exists.
         threads: int - The number of cpu threads to use per worker, e.g. will be multiplied by num workers.
     Returns:
         A Whisper pipeline.
@@ -290,6 +294,7 @@ def load_model(whisper_arch,
                          device_index=device_index,
                          compute_type=compute_type,
                          download_root=download_root,
+                         local_files_only=local_files_only,
                          cpu_threads=threads)
     if language is not None:
         tokenizer = faster_whisper.tokenizer.Tokenizer(model.hf_tokenizer, model.model.is_multilingual, task=task, language=language)
@@ -319,10 +324,12 @@ def load_model(whisper_arch,
         "word_timestamps": False,
         "prepend_punctuations": "\"'“¿([{-",
         "append_punctuations": "\"'.。,，!！?？:：”)]}、",
+        "multilingual": model.model.is_multilingual,
         "suppress_numerals": False,
         "max_new_tokens": None,
         "clip_timestamps": None,
         "hallucination_silence_threshold": None,
+        "hotwords": None,
     }
 
     if asr_options is not None:
@@ -354,4 +361,4 @@ def load_model(whisper_arch,
         language=language,
         suppress_numerals=suppress_numerals,
         vad_params=default_vad_options,
-    )
+    )

whisperx/transcribe.py

@@ -87,6 +87,7 @@ def cli():
     device: str = args.pop("device")
     device_index: int = args.pop("device_index")
     compute_type: str = args.pop("compute_type")
+    verbose: bool = args.pop("verbose")
 
     # model_flush: bool = args.pop("model_flush")
     os.makedirs(output_dir, exist_ok=True)
@@ -173,7 +174,7 @@ def cli():
         audio = load_audio(audio_path)
         # >> VAD & ASR
         print(">>Performing transcription...")
-        result = model.transcribe(audio, batch_size=batch_size, chunk_size=chunk_size, print_progress=print_progress)
+        result = model.transcribe(audio, batch_size=batch_size, chunk_size=chunk_size, print_progress=print_progress, verbose=verbose)
         results.append((result, audio_path))
 
     # Unload Whisper and VAD