voxmlx 0.0.1__tar.gz

voxmlx-0.0.1/.gitignore

@@ -0,0 +1,210 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# vim
+*.swp
+
+# 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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

voxmlx-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Awni Hannun
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

voxmlx-0.0.1/PKG-INFO

@@ -0,0 +1,96 @@
+Metadata-Version: 2.4
+Name: voxmlx
+Version: 0.0.1
+Summary: Voxtral Mini Realtime speech-to-text in MLX
+License: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mlx>=0.20.0
+Requires-Dist: numpy
+Requires-Dist: soundfile
+Requires-Dist: sounddevice
+Requires-Dist: huggingface-hub
+Requires-Dist: sentencepiece
+Dynamic: license-file
+
+# voxmlx
+
+Realtime speech-to-text with
+[Voxtral Mini Realtime](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602)
+in [MLX](https://github.com/ml-explore/mlx).
+
+## Install
+
+```bash
+pip install voxmlx
+```
+
+## Usage
+
+### `voxmlx`
+
+Transcribe audio from a file or stream from the microphone in real-time.
+
+**Stream from microphone:**
+
+```bash
+voxmlx
+```
+
+**Transcribe a file:**
+
+```bash
+voxmlx --audio audio.flac
+```
+
+**Options:**
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--audio` | Path to audio file (omit to stream from mic) | None |
+| `--model` | Model path or HuggingFace model ID | `mlx-community/Voxtral-Mini-4B-Realtime-6bit` |
+| `--temp` | Sampling temperature (`0` = greedy) | `0.0` |
+
+### `voxmlx-convert`
+
+Convert Voxtral weights to voxmlx/MLX format with optional quantization.
+
+**Basic conversion:**
+
+```bash
+voxmlx-convert --mlx-path voxtral-mlx
+```
+
+**4-bit quantized conversion:**
+
+```bash
+voxmlx-convert -q --mlx-path voxtral-mlx-4bit
+```
+
+**Convert and upload to HuggingFace:**
+
+```bash
+voxmlx-convert -q --mlx-path voxtral-mlx-4bit --upload-repo username/voxtral-mlx-4bit
+```
+
+**Options:**
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--hf-path` | HuggingFace model ID or local path | `mistralai/Voxtral-Mini-4B-Realtime-2602` |
+| `--mlx-path` | Output directory | `mlx_model` |
+| `-q`, `--quantize` | Quantize the model | Off |
+| `--group-size` | Quantization group size | `64` |
+| `--bits` | Bits per weight | `4` |
+| `--dtype` | Cast weights (`float16`, `bfloat16`, `float32`) | None |
+| `--upload-repo` | HuggingFace repo to upload converted model | None |
+
+### Python API
+
+```python
+from voxmlx import transcribe
+
+text = transcribe("audio.flac")
+print(text)
+```

voxmlx-0.0.1/README.md

@@ -0,0 +1,80 @@
+# voxmlx
+
+Realtime speech-to-text with
+[Voxtral Mini Realtime](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602)
+in [MLX](https://github.com/ml-explore/mlx).
+
+## Install
+
+```bash
+pip install voxmlx
+```
+
+## Usage
+
+### `voxmlx`
+
+Transcribe audio from a file or stream from the microphone in real-time.
+
+**Stream from microphone:**
+
+```bash
+voxmlx
+```
+
+**Transcribe a file:**
+
+```bash
+voxmlx --audio audio.flac
+```
+
+**Options:**
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--audio` | Path to audio file (omit to stream from mic) | None |
+| `--model` | Model path or HuggingFace model ID | `mlx-community/Voxtral-Mini-4B-Realtime-6bit` |
+| `--temp` | Sampling temperature (`0` = greedy) | `0.0` |
+
+### `voxmlx-convert`
+
+Convert Voxtral weights to voxmlx/MLX format with optional quantization.
+
+**Basic conversion:**
+
+```bash
+voxmlx-convert --mlx-path voxtral-mlx
+```
+
+**4-bit quantized conversion:**
+
+```bash
+voxmlx-convert -q --mlx-path voxtral-mlx-4bit
+```
+
+**Convert and upload to HuggingFace:**
+
+```bash
+voxmlx-convert -q --mlx-path voxtral-mlx-4bit --upload-repo username/voxtral-mlx-4bit
+```
+
+**Options:**
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--hf-path` | HuggingFace model ID or local path | `mistralai/Voxtral-Mini-4B-Realtime-2602` |
+| `--mlx-path` | Output directory | `mlx_model` |
+| `-q`, `--quantize` | Quantize the model | Off |
+| `--group-size` | Quantization group size | `64` |
+| `--bits` | Bits per weight | `4` |
+| `--dtype` | Cast weights (`float16`, `bfloat16`, `float32`) | None |
+| `--upload-repo` | HuggingFace repo to upload converted model | None |
+
+### Python API
+
+```python
+from voxmlx import transcribe
+
+text = transcribe("audio.flac")
+print(text)
+```

voxmlx-0.0.1/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["setuptools", "setuptools-scm"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "voxmlx"
+dynamic = ["version"]
+description = "Voxtral Mini Realtime speech-to-text in MLX"
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.10"
+dependencies = [
+    "mlx>=0.20.0",
+    "numpy",
+    "soundfile",
+    "sounddevice",
+    "huggingface-hub",
+    "sentencepiece",
+]
+
+[tool.setuptools.dynamic]
+version = {attr = "voxmlx.__version__"}
+
+[project.scripts]
+voxmlx = "voxmlx:main"
+voxmlx-convert = "voxmlx.convert:main"

voxmlx-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

voxmlx-0.0.1/voxmlx/__init__.py

@@ -0,0 +1,81 @@
+__version__ = "0.0.1"
+
+import argparse
+from pathlib import Path
+
+from mistral_common.tokens.tokenizers.base import SpecialTokenPolicy
+from mistral_common.tokens.tokenizers.tekken import Tekkenizer
+
+from .generate import generate
+from .weights import download_model, load_model as _load_weights
+
+
+def _load_tokenizer(model_path: Path) -> Tekkenizer:
+    tekken_path = model_path / "tekken.json"
+    return Tekkenizer.from_file(str(tekken_path))
+
+
+def _build_prompt_tokens(
+    sp: Tekkenizer,
+    n_left_pad_tokens: int = 32,
+    num_delay_tokens: int = 6,
+) -> tuple[list[int], int]:
+    streaming_pad = sp.get_special_token("[STREAMING_PAD]")
+    prefix_len = n_left_pad_tokens + num_delay_tokens  # 38 STREAMING_PAD tokens
+    tokens = [sp.bos_id] + [streaming_pad] * prefix_len
+    return tokens, num_delay_tokens
+
+
+def load_model(model_path: str = "mlx-community/Voxtral-Mini-4B-Realtime-6bit"):
+    if not Path(model_path).exists():
+        model_path = download_model(model_path)
+    else:
+        model_path = Path(model_path)
+
+    model, config = _load_weights(model_path)
+    sp = _load_tokenizer(model_path)
+    return model, sp, config
+
+
+def transcribe(
+    audio_path: str,
+    model_path: str = "mlx-community/Voxtral-Mini-4B-Realtime-6bit",
+    temperature: float = 0.0,
+) -> str:
+    model, sp, config = load_model(model_path)
+
+    prompt_tokens, n_delay_tokens = _build_prompt_tokens(sp)
+
+    output_tokens = generate(
+        model,
+        audio_path,
+        prompt_tokens,
+        n_delay_tokens=n_delay_tokens,
+        temperature=temperature,
+        eos_token_id=sp.eos_id,
+    )
+
+    return sp.decode(output_tokens, special_token_policy=SpecialTokenPolicy.IGNORE)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Voxtral Mini Realtime speech-to-text")
+    parser.add_argument("--audio", default=None, help="Path to audio file (omit to stream from mic)")
+    parser.add_argument("--model", default="mlx-community/Voxtral-Mini-4B-Realtime-6bit", help="Model path or HF model ID")
+    parser.add_argument("--temp", type=float, default=0.0, help="Sampling temperature (0 = greedy)")
+    args = parser.parse_args()
+
+    if args.audio is not None:
+        text = transcribe(
+            args.audio,
+            model_path=args.model,
+            temperature=args.temp,
+        )
+        print(text)
+    else:
+        from .stream import stream_transcribe
+
+        stream_transcribe(
+            model_path=args.model,
+            temperature=args.temp,
+        )