libspeech 0.2.0__cp312-abi3-win_amd64.whl

libspeech/__init__.py

@@ -0,0 +1,114 @@
+from __future__ import annotations
+
+import os
+import sys
+from ctypes import *
+from pathlib import Path
+
+_here = Path(__file__).parent
+
+# On Windows, loading one DLL (e.g. speech.dll) that itself implicitly
+# needs another (httpp_core.dll, onnxruntime.dll) only searches a fixed
+# set of directories for that dependency -- the loading DLL's own
+# directory, System32, PATH, etc -- which does NOT include wherever we
+# explicitly cdll.LoadLibrary() a dependency FROM if that happens to be
+# some other, unrelated directory (httpp's own install dir is nowhere
+# near libspeech's). os.add_dll_directory() (the mechanism Python 3.8+
+# itself introduced to replace the old implicit-PATH/CWD search it
+# removed for security reasons) adds a directory to that search list for
+# the rest of the process, so speech.dll's own implicit dependency
+# resolution can actually find libhttpp_core.so/httpp_core.dll wherever
+# httpp really lives, not just next to speech.dll itself.
+if sys.platform == "win32":
+    os.add_dll_directory(str(_here))
+
+# ONNXRuntime and speech itself each ship as a separate shared library we
+# load explicitly before importing the compiled extensions (they dlopen
+# symbols from these at import time). Both get bundled right next to this
+# __init__.py by CMakeLists.txt (see the SKBUILD install() rule / the
+# local dev build's LIBRARY_OUTPUT_DIRECTORY) rather than found via
+# RPATH: an RPATH baked in at build time would only point back at
+# wherever the ONNXRuntime download happened to land on the *build*
+# machine, which has no reason to exist -- or be the same path -- on
+# whatever machine later installs this wheel. Loading a bundled copy by
+# explicit path here works regardless of where/how this package itself
+# ends up installed.
+#
+# Each filename varies by platform (libspeech.so / speech.dll /
+# libspeech.dylib), and ONNXRuntime's is version-suffixed on top of that
+# (e.g. libonnxruntime.so.1.21.0). Rather than guess any of that here
+# (hardcoding one platform's name, or globbing for a pattern that only
+# happens to match some platforms), CMake computes the exact filename it
+# actually produced for each one and bakes it into _about -- see the
+# target_compile_definitions() call on the _about target in
+# CMakeLists.txt, and about.cpp. _about is itself a tiny, dependency-free
+# compiled module (no link against speech/httpp/ONNXRuntime), so it's
+# safe to import before any of those are loaded.
+from ._about import HTTPP_LIB_PATH, LIB_PATH, ONNXRUNTIME_LIB_PATH, __version__
+
+# httpp is a separate package (pip install httpp), not bundled inside
+# libspeech -- loaded straight from wherever the installed httpp package
+# actually lives, via httpp's own get_lib_dir() helper, so libspeech
+# always runs against whatever httpp build is really installed rather
+# than a copy shipped in here. This is a normal Python import, so it
+# works the same way on every platform and in a local dev build too (no
+# site-packages layout to assume, no symlink needed) -- httpp only has to
+# be importable, same as any other Python dependency.
+try:
+    import httpp
+except ImportError as e:
+    msg = "libspeech requires the 'httpp' package. Install it with: pip install httpp"
+    raise ImportError(msg) from e
+
+_httpp_lib_dir = Path(httpp.get_lib_dir())
+if sys.platform == "win32":
+    os.add_dll_directory(str(_httpp_lib_dir))
+
+# HTTPP_LIB_PATH is only the filename (computed by CMake, see above);
+# httpp.get_lib_dir() is httpp's own answer for where that filename lives.
+cdll.LoadLibrary(str(_httpp_lib_dir / HTTPP_LIB_PATH))
+
+cdll.LoadLibrary(str(_here / ONNXRUNTIME_LIB_PATH))
+
+# NOTE: AudioFlux is statically linked into libspeech.so itself (see
+# CMakeLists.txt: speech_dsp/speech_models are STATIC libraries), so there
+# is no separate libaudioflux.so to preload here -- only libspeech.so
+# itself needs an explicit load (httpp and ONNXRuntime, both dynamically
+# linked, were already preloaded above).
+cdll.LoadLibrary(str(_here / LIB_PATH))
+from .speech_dsp_py import (
+    FFT,
+    MFCC,
+    STFT,
+    MFCCParams,
+    Resample,
+    WindowType,
+    dct,
+    window,
+)
+
+# The compiled extension modules (_about, speech_io_py, ...) are
+# intentionally underscore/private-prefixed and not meant to be imported
+# directly by users -- `import libspeech; libspeech.Audio(...)`, not
+# `import speech_io_py`. Re-export the public names here, matching ctoon's
+# `from .ctoon_py import *` pattern. Module names mirror the CMake target
+# names (speech_dsp/speech_io/speech_models -> speech_dsp_py/speech_io_py/
+# speech_models_py) so the two naming schemes stay in sync.
+from .speech_io_py import Audio
+from .speech_models_py import Denoiser, SileroVad, SpeechTimestamp
+
+__all__ = [
+    "FFT",
+    "MFCC",
+    "STFT",
+    "Audio",
+    "Denoiser",
+    "MFCCParams",
+    "Resample",
+    "SileroVad",
+    "SpeechTimestamp",
+    "WindowType",
+    "__version__",
+    "dct",
+    "window",
+]

libspeech/__main__.py

@@ -0,0 +1,33 @@
+#!/bin/python3
+from __future__ import annotations
+
+import argparse
+import sys
+
+from . import Host, Url, __doc__, __version__
+
+
+def show_if_not_none(_str, _class):
+    if _str is not None:
+        print(_class(_str).to_json())
+
+
+def main(args):
+    show_if_not_none(args.url, Url)
+    show_if_not_none(args.host, Host)
+    if args.version:
+        print(__version__)
+    if args.doc:
+        print(__doc__)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--url", type=str, default=None,
+                        help="enter entire url (for example: \"https://google.com/about\")")
+    parser.add_argument("--host", type=str, default=None,
+                        help="enter just host part of url (for example: \"google.com\")")
+    parser.add_argument('-v', '--version', action='store_true', help="showing version of module")
+    parser.add_argument('--doc', action='store_true', help="showing version of module")
+    args = parser.parse_args(args=None if sys.argv[1:] else ['--help'])
+    main(args)

libspeech/core.py

@@ -0,0 +1,15 @@
+#!/bin/python3
+from __future__ import annotations
+
+import warnings
+from pathlib import Path
+
+# ctypes.CDLL(Path(__file__).parent/"libspeech.so")
+from ._audio import Audio
+
+
+def warning_on_one_line(message, category, filename, lineno, file=None, line=None):
+    return f'{filename}:{lineno}: {category.__name__}: {message}\n'
+
+
+

libspeech-0.2.0.dist-info/METADATA

@@ -0,0 +1,221 @@
+Metadata-Version: 2.2
+Name: libspeech
+Version: 0.2.0
+Summary: Best library for speech
+Author-Email: Mohammad Raziei <mohammadraziei1375@gmail.com>
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: C++
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Project-URL: Homepage, https://github.com/mohammadraziei/libspeech
+Project-URL: Bug Tracker, https://github.com/mohammadraziei/libspeech/issues
+Project-URL: Document, https://mohammadraziei.github.io/libspeech/latest
+Requires-Python: >=3.8
+Requires-Dist: httpp>=0.6.0
+Provides-Extra: test
+Requires-Dist: pytest-xdist; extra == "test"
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <a href="https://github.com/mohammadraziei/libspeech">
+    <img src="https://raw.githubusercontent.com/MohammadRaziei/libspeech/master/docs/logo/libspeech-logo-pods.svg" alt="LibSpeech Logo" width="300">
+  </a>
+  <h2 align="center">LibSpeech</h2>
+  <h3 align="center">Lightweight Speech Processing Library</h3>
+</p>
+
+<p align="center">
+  <em>C++ library with Python bindings for audio I/O, DSP, and ONNX-based speech models -- built to install with nothing but <code>pip</code>, no system dependencies (libcurl, OpenSSL, ...) required.</em>
+</p>
+
+<div align="center">
+
+[![GitHub release](https://img.shields.io/github/release/mohammadraziei/libspeech?color=blue)](https://github.com/mohammadraziei/libspeech/releases)
+[![License](https://img.shields.io/badge/license-MIT-purple)](LICENSE)
+[![Python Versions](https://img.shields.io/pypi/pyversions/libspeech)](https://pypi.org/project/libspeech/)
+[![C++ Standard](https://img.shields.io/badge/C++-17-blue)](https://en.cppreference.com/w/cpp/17)
+
+[![Build Status](https://github.com/mohammadraziei/libspeech/actions/workflows/build.yml/badge.svg)](https://github.com/mohammadraziei/libspeech/actions)
+[![Code Quality](https://sonarcloud.io/api/project_badges/measure?project=MohammadRaziei_libspeech&metric=alert_status)](https://sonarcloud.io/summary/new_code?id=MohammadRaziei_libspeech)
+[![CodeFactor](https://www.codefactor.io/repository/github/mohammadraziei/libspeech/badge/master)](https://www.codefactor.io/repository/github/mohammadraziei/libspeech/overview/master)
+[![snyk.io](https://snyk.io/advisor/python/libspeech/badge.svg)](https://snyk.io/advisor/python/libspeech)
+[![PyPI Downloads](https://img.shields.io/pypi/dm/libspeech)](https://pypi.org/project/libspeech/)
+
+</div>
+
+## ✨ Key Features
+
+- 🚀 **ONNX Runtime powered** models, without a heavy LibTorch dependency
+- 🎙️ **Audio I/O** (`speech::io`): load/save WAV/MP3/FLAC, playback, resample, mono-mixing
+- 🧮 **DSP** (`speech::dsp`): Resample, window functions, FFT/IFFT, DCT/IDCT, STFT/ISTFT, MFCC -- all with their own C++ unit tests and Python bindings
+- 🔊 **Speech models** (`speech::models`): a `Denoiser` interface (Facebook/SpeechBrain backends) and Silero VAD
+- 🖥️ **Cross-platform**: Windows, Linux, macOS
+- 🐍 **Python bindings** (nanobind) mirroring the C++ API 1:1
+- 📦 **Zero system dependencies**: no `apt install libcurl-dev` / OpenSSL needed -- HTTPS model downloads go through a vendored [cpp-httplib](https://github.com/yhirose/cpp-httplib) + [Mbed TLS](https://github.com/Mbed-TLS/mbedtls) built from source
+
+## 📦 Installation
+
+### Python package
+```bash
+pip install libspeech
+```
+
+### From source (C++/CMake)
+```bash
+git clone https://github.com/MohammadRaziei/libspeech.git
+cd libspeech
+git submodule update --init src/third_party/miniaudio src/third_party/dr_libs src/third_party/indicators
+
+# Mbed TLS is pinned to v3.6.2 and kept as a shallow submodule (see .gitmodules):
+git submodule update --init src/third_party/mbedtls
+git submodule update --init --depth 1 src/third_party/mbedtls/framework
+
+mkdir build && cd build
+cmake ..                      # downloads ONNX Runtime automatically on first configure
+cmake --build . -j$(nproc)
+ctest                         # runs the full test suite (see "Testing" below)
+```
+
+Only want the DSP layer (no ONNX Runtime/network access needed at all)?
+```bash
+cmake .. -DBUILD_MODELS=OFF
+cmake --build . -j$(nproc)
+```
+
+## 🚀 Quick Start
+
+### Python
+
+```python
+import libspeech
+
+# --- Audio I/O ---
+audio = libspeech.Audio()
+audio.load("sample.wav")
+mono = audio.to_mono()
+resampled = mono.resample(16000)
+resampled.save("sample_16k_mono.wav")
+
+# --- DSP ---
+mfcc = libspeech.MFCC(libspeech.MFCCParams())
+coefficients = mfcc.compute(resampled.data(0))   # [num_frames][num_coefficients]
+
+# --- Speech models ---
+denoiser = libspeech.Denoiser.create("facebook", "facebook_denoiser.onnx")
+clean = denoiser.process(resampled.data(0))
+
+vad = libspeech.SileroVad()
+vad.process(resampled.data(0))
+for segment in vad.get_speech_timestamps():
+    print(f"speech from {segment.start_s:.2f}s to {segment.end_s:.2f}s")
+```
+
+### C++
+
+```cpp
+#include "libspeech/audio.h"
+#include "libspeech/dsp/mfcc.h"
+#include "libspeech/models/denoiser.h"
+
+speech::io::Audio audio;
+audio.load("sample.wav");
+auto resampled = audio.to_mono().resample(16000);
+
+speech::dsp::MFCC::Params params;
+params.sampleRate = 16000;
+speech::dsp::MFCC mfcc(params);
+auto coefficients = mfcc.compute(resampled.data(0));
+
+auto denoiser = speech::models::Denoiser::Create("facebook", "facebook_denoiser.onnx");
+auto clean = denoiser->process(resampled.data(0));
+```
+
+See [`examples/`](examples/) for complete, runnable programs.
+
+## 🧪 Testing
+
+Tests are organized by language and module (`speech_test_<language>_<module>`),
+all discoverable via `cmake --build build --target help`:
+
+```
+speech_test                       # everything
+├── speech_test_cpp
+│   ├── speech_test_cpp_dsp       # speech::dsp (C++), no network/ONNX needed
+│   └── speech_test_cpp_models    # speech::models (C++)
+└── speech_test_python
+    ├── speech_test_python_audio  # libspeech.Audio
+    ├── speech_test_python_dsp    # libspeech.Resample/FFT/STFT/MFCC/...
+    └── speech_test_python_models # libspeech.Denoiser/SileroVad
+```
+
+Run everything with `cmake --build build --target speech_test`, or just
+`ctest` for the same suites without the extra build-tool chatter.
+
+## 🔧 Architecture
+
+libspeech is split into three independent C++ libraries (each with its own
+CMake target/namespace/Python module), aggregated by an umbrella `speech`
+library:
+
+| Namespace | CMake target | Python module | Depends on |
+|---|---|---|---|
+| `speech::dsp` | `speech_dsp` | `speech_dsp_py` | nothing but a vendored subset of [AudioFlux](https://github.com/libAudioFlux/audioflux)'s C sources |
+| `speech::io` | `speech_io` | `speech_io_py` | `speech::dsp` (for resampling), miniaudio, dr_libs |
+| `speech::models` | `speech_models` | `speech_models_py` | ONNX Runtime, httplib+Mbed TLS (for downloading model weights) |
+
+See [`checklist.md`](checklist.md) for the detailed, up-to-date state of
+the project (what's done, what's in progress, known issues), and
+[`audioflux_issues.md`](audioflux_issues.md) for a couple of real bugs
+found in AudioFlux while vendoring it (with repro steps and fixes, in case
+they're useful upstream).
+
+## 📊 Benchmarking
+
+`benchmarks/` is a **fully standalone** CMake project (no relationship to
+the repository root) that fetches libspeech from GitHub via
+`FetchContent`, exactly like it would fetch any competitor library --
+libspeech is never a special case in there. Mirrors the layout of
+`tests/`: one folder per language.
+
+```bash
+cd benchmarks
+cmake -S . -B build-bench -DCMAKE_BUILD_TYPE=Release
+cmake --build build-bench --target libspeech_benchmarks
+```
+
+`benchmarks/cpp/bench_stft.cpp` measures `speech::dsp::STFT`, specifically
+to A/B test whether enabling OpenMP's parallel-frame path
+(`LIBSPEECH_ENABLE_OPENMP`, on by default) actually helps -- STFT frames
+are independent so this *should* scale with core count, but this couldn't
+be verified in this project's own single-core development sandbox (see
+`checklist.md`). If you have a multi-core machine, please run this and
+report back:
+
+```bash
+cmake -S . -B build-bench -DCMAKE_BUILD_TYPE=Release -DLIBSPEECH_ENABLE_OPENMP=ON
+cmake --build build-bench --target bench_stft && ./build-bench/cpp/bench_stft
+
+cmake -S . -B build-bench -DLIBSPEECH_ENABLE_OPENMP=OFF
+cmake --build build-bench --target bench_stft && ./build-bench/cpp/bench_stft
+```
+
+Compare the two `avg=...ms` numbers -- that's the real effect of enabling
+OpenMP on your hardware.
+
+## 🤝 Contributing
+
+We welcome contributions! Please see [`CONTRIBUTING.md`](CONTRIBUTING.md).
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+[![Stars](https://starchart.cc/mohammadraziei/libspeech.svg?variant=adaptive)](https://starchart.cc/mohammadraziei/libspeech)

libspeech-0.2.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+libspeech/__init__.py,sha256=ctTxTgDL13LXnct8zDMVO50vinM_xDNujvIM8eBY3-w,5019
+libspeech/__main__.py,sha256=RfOmaGYL-JqkHol9P6oPpFleqDluBvFETN7GcQfCLjY,1078
+libspeech/_about.pyd,sha256=PWIlzTI5MwMHsu5zVUIm54joH6wGYaN6ZLhPRP74Grs,148480
+libspeech/core.py,sha256=UHoSTx6ydjjs47CX8FrsYtdopDugscWOHY9v8F5RAGw,343
+libspeech/onnxruntime.dll,sha256=KiR4m7BnaP5B5Sh8o_NYUYYbx5AtL1v2jGu5pNw8czI,13006392
+libspeech/onnxruntime_providers_shared.dll,sha256=YJihQCMYsg-C-oh5gTWeY7A5R9AfvHcbJXevikT_ttE,22048
+libspeech/speech.dll,sha256=tccTTQ7-LGkbZqJJCBdKwtGn_VHVmYa8vN0Th60N8Vg,797696
+libspeech/speech_audio_py.pyd,sha256=9J22W_80j0cmsFZEawCNCG_wXUtOCYN-V6fWOAlym0A,164352
+libspeech/speech_dsp_py.pyd,sha256=rbSAz9gzyDQ7tMTcSfLEoj2QKQY4jSkPLlvCVK10pCo,170496
+libspeech/speech_io_py.pyd,sha256=ZPgo_cg1ML7QkkxNeIfTu7gKR-xmuf6MYnf2Cbv5Eeo,164352
+libspeech/speech_models_py.pyd,sha256=zZMjHD2yhTEkvyNnkWd504bevvMuo29otl2rdPh_y2g,162816
+libspeech-0.2.0.dist-info/METADATA,sha256=i4Hsd-zZDd0WHE7QKH0sxyXpdtlmCbBBhxHQprM0l2Q,9210
+libspeech-0.2.0.dist-info/WHEEL,sha256=5ml-wNaeRKDYXu-TApi0xYDjo761u9hbeCC2pq12vdU,104
+libspeech-0.2.0.dist-info/licenses/LICENSE,sha256=N_R9-5l0U5HZyk0-el1LtB0nxSXttAIy78h4x_w_bgk,2218
+libspeech-0.2.0.dist-info/RECORD,,

libspeech-0.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: scikit-build-core 1.1.0
+Root-Is-Purelib: false
+Tag: cp312-abi3-win_amd64
+

libspeech-0.2.0.dist-info/licenses/LICENSE

@@ -0,0 +1,36 @@
+Copyright (c) 2016 The Pybind Development Team, All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its contributors
+   may be used to endorse or promote products derived from this software
+   without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+You are under no obligation whatsoever to provide any bug fixes, patches, or
+upgrades to the features, functionality or performance of the source code
+("Enhancements") to anyone; however, if you choose to make your Enhancements
+available either publicly, or directly to the author of this software, without
+imposing a separate written license agreement for such Enhancements, then you
+hereby grant the following license: a non-exclusive, royalty-free perpetual
+license to install, use, modify, prepare derivative works, incorporate into
+other computer software, distribute, and sublicense such enhancements or
+derivative works thereof, in binary and source code form.