visqol-python 3.3.3__tar.gz

visqol_python-3.3.3/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

visqol_python-3.3.3/MANIFEST.in

@@ -0,0 +1,4 @@
+include README.md
+include LICENSE
+include requirements.txt
+recursive-include visqol/model *.txt

visqol_python-3.3.3/PKG-INFO

@@ -0,0 +1,223 @@
+Metadata-Version: 2.4
+Name: visqol-python
+Version: 3.3.3
+Summary: ViSQOL - Virtual Speech Quality Objective Listener (Pure Python)
+Home-page: https://github.com/talker93/visqol-python
+Author: Shan Jiang
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/talker93/visqol-python
+Project-URL: Bug Reports, https://github.com/talker93/visqol-python/issues
+Project-URL: Source, https://github.com/talker93/visqol-python
+Project-URL: Original C++, https://github.com/google/visqol
+Keywords: audio-quality,speech-quality,MOS,PESQ,POLQA,visqol,objective-metric,perceptual-quality
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+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
+Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.20
+Requires-Dist: scipy>=1.7
+Requires-Dist: soundfile>=0.10
+Requires-Dist: libsvm-official>=3.25
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# ViSQOL (Python)
+
+A pure Python implementation of [Google's ViSQOL](https://github.com/google/visqol) (Virtual Speech Quality Objective Listener) v3.3.3 for objective audio/speech quality assessment.
+
+ViSQOL compares a reference audio signal with a degraded version and outputs a **MOS-LQO** (Mean Opinion Score - Listening Quality Objective) score on a scale of **1.0 – 5.0**.
+
+## Features
+
+- **Two modes**: Audio mode (music/general audio at 48 kHz) and Speech mode (speech at 16 kHz)
+- **High accuracy**: 11/11 conformance tests pass against the official C++ implementation
+  - Audio mode: 9/10 tests produce **identical** MOS scores (diff = 0.000000), 1 test diff = 0.000117
+  - Speech mode: diff = 0.006715
+- **Pure Python**: no C/C++ compilation required
+- **Minimal dependencies**: only 4 pip packages (`numpy`, `scipy`, `soundfile`, `libsvm-official`)
+- **Faster than real-time**: Audio RTF ≈ 0.71x, Speech RTF ≈ 0.38x
+
+## Installation
+
+```bash
+pip install numpy scipy soundfile libsvm-official
+```
+
+Or install as a package:
+
+```bash
+git clone https://github.com/talker93/visqol-python.git
+cd visqol-python
+pip install -e .
+```
+
+## Quick Start
+
+### Python API
+
+```python
+from visqol import VisqolApi
+
+# Audio mode (default) - for music and general audio
+api = VisqolApi()
+api.create(mode="audio")
+result = api.measure("reference.wav", "degraded.wav")
+print(f"MOS-LQO: {result.moslqo:.4f}")
+
+# Speech mode - for speech signals
+api = VisqolApi()
+api.create(mode="speech")
+result = api.measure("ref_speech.wav", "deg_speech.wav")
+print(f"MOS-LQO: {result.moslqo:.4f}")
+```
+
+### Using NumPy Arrays
+
+```python
+import numpy as np
+import soundfile as sf
+from visqol import VisqolApi
+
+ref, sr = sf.read("reference.wav")
+deg, _  = sf.read("degraded.wav")
+
+api = VisqolApi()
+api.create(mode="audio")
+result = api.measure_from_arrays(ref, deg, sample_rate=sr)
+print(f"MOS-LQO: {result.moslqo:.4f}")
+```
+
+### Command Line
+
+```bash
+# Audio mode (default)
+python -m visqol -r reference.wav -d degraded.wav
+
+# Speech mode
+python -m visqol -r reference.wav -d degraded.wav --speech_mode
+
+# Verbose output (per-patch details)
+python -m visqol -r reference.wav -d degraded.wav -v
+```
+
+**CLI options:**
+
+| Flag | Description |
+|------|-------------|
+| `-r`, `--reference` | Path to reference WAV file (required) |
+| `-d`, `--degraded` | Path to degraded WAV file (required) |
+| `--speech_mode` | Use speech mode (16 kHz, polynomial mapping) |
+| `--model` | Custom SVR model file path (audio mode only) |
+| `--search_window` | Search window radius (default: 60) |
+| `--verbose`, `-v` | Show detailed per-patch results |
+
+## Output
+
+The `measure()` method returns a `SimilarityResult` object with:
+
+| Field | Description |
+|-------|-------------|
+| `moslqo` | MOS-LQO score (1.0 – 5.0) |
+| `vnsim` | Mean NSIM across all patches |
+| `fvnsim` | Per-frequency-band mean NSIM |
+| `fstdnsim` | Per-frequency-band std of NSIM |
+| `fvdegenergy` | Per-frequency-band degraded energy |
+| `patch_sims` | List of per-patch similarity details |
+
+## Modes
+
+### Audio Mode (default)
+- Target sample rate: **48 kHz**
+- 32 Gammatone frequency bands (50 Hz – 15 000 Hz)
+- Quality mapping: SVR (Support Vector Regression) model
+- Best for: music, environmental audio, codecs
+
+### Speech Mode
+- Target sample rate: **16 kHz**
+- 32 Gammatone frequency bands (50 Hz – 8 000 Hz)
+- Quality mapping: exponential polynomial fit
+- VAD (Voice Activity Detection) based patch selection
+- Best for: speech, VoIP, telephony
+
+## Performance
+
+Measured on Apple M-series, Python 3.13:
+
+| Mode | Avg RTF | Typical Time |
+|------|---------|-------------|
+| Audio (48 kHz) | **0.71x** | 7 – 12 s per file pair |
+| Speech (16 kHz) | **0.38x** | ~1 s per file pair |
+
+> RTF (Real-Time Factor) < 1.0 means faster than real-time.
+
+## Project Structure
+
+```
+visqol-python/
+├── visqol/                    # Main package
+│   ├── __init__.py            # Package exports
+│   ├── api.py                 # Public API
+│   ├── visqol_manager.py      # Pipeline orchestrator
+│   ├── visqol_core.py         # Core algorithm
+│   ├── audio_utils.py         # Audio I/O & SPL normalization
+│   ├── signal_utils.py        # Envelope, cross-correlation
+│   ├── analysis_window.py     # Hann window
+│   ├── gammatone.py           # ERB + Gammatone filterbank + spectrogram
+│   ├── patch_creator.py       # Patch creation (Image + VAD modes)
+│   ├── patch_selector.py      # DP-based optimal patch matching
+│   ├── alignment.py           # Global alignment via cross-correlation
+│   ├── nsim.py                # NSIM similarity metric
+│   ├── quality_mapper.py      # SVR & exponential quality mapping
+│   └── __main__.py            # CLI entry point
+├── model/                     # Bundled SVR model
+│   └── libsvm_nu_svr_model.txt
+├── tests/                     # Conformance tests
+│   ├── test_conformance.py
+│   └── test_quick.py
+├── setup.py
+├── requirements.txt
+├── LICENSE
+└── README.md
+```
+
+## Conformance Test Results
+
+Tested against the [official C++ ViSQOL v3.3.3](https://github.com/google/visqol) expected values:
+
+| Test Case | Mode | Expected MOS | Python MOS | Δ |
+|-----------|------|-------------|------------|---|
+| strauss_lp35 | Audio | 1.3889 | 1.3889 | 0.000000 |
+| steely_lp7 | Audio | 2.2502 | 2.2502 | 0.000000 |
+| sopr_256aac | Audio | 4.6823 | 4.6823 | 0.000000 |
+| ravel_128opus | Audio | 4.4651 | 4.4651 | 0.000000 |
+| moonlight_128aac | Audio | 4.6843 | 4.6843 | 0.000000 |
+| harpsichord_96mp3 | Audio | 4.2237 | 4.2237 | 0.000000 |
+| guitar_64aac | Audio | 4.3497 | 4.3497 | 0.000000 |
+| glock_48aac | Audio | 4.3325 | 4.3325 | 0.000000 |
+| contrabassoon_24aac | Audio | 2.3469 | 2.3468 | 0.000117 |
+| castanets_identity | Audio | 4.7321 | 4.7321 | 0.000000 |
+| speech_CA01 | Speech | 3.3745 | 3.3678 | 0.006715 |
+
+## References
+
+- [Google ViSQOL (C++)](https://github.com/google/visqol) — the original implementation this project is ported from
+- Hines, A., Gillen, E., Kelly, D., Skoglund, J., Kokaram, A., & Harte, N. (2015). *ViSQOLAudio: An Objective Audio Quality Metric for Low Bitrate Codecs.* The Journal of the Acoustical Society of America.
+- Chinen, M., Lim, F. S., Skoglund, J., Gureev, N., O'Gorman, F., & Hines, A. (2020). *ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric.* 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX).
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE) for details.
+
+This project is a Python port of [Google's ViSQOL](https://github.com/google/visqol), which is also licensed under Apache 2.0.

visqol_python-3.3.3/README.md

@@ -0,0 +1,188 @@
+# ViSQOL (Python)
+
+A pure Python implementation of [Google's ViSQOL](https://github.com/google/visqol) (Virtual Speech Quality Objective Listener) v3.3.3 for objective audio/speech quality assessment.
+
+ViSQOL compares a reference audio signal with a degraded version and outputs a **MOS-LQO** (Mean Opinion Score - Listening Quality Objective) score on a scale of **1.0 – 5.0**.
+
+## Features
+
+- **Two modes**: Audio mode (music/general audio at 48 kHz) and Speech mode (speech at 16 kHz)
+- **High accuracy**: 11/11 conformance tests pass against the official C++ implementation
+  - Audio mode: 9/10 tests produce **identical** MOS scores (diff = 0.000000), 1 test diff = 0.000117
+  - Speech mode: diff = 0.006715
+- **Pure Python**: no C/C++ compilation required
+- **Minimal dependencies**: only 4 pip packages (`numpy`, `scipy`, `soundfile`, `libsvm-official`)
+- **Faster than real-time**: Audio RTF ≈ 0.71x, Speech RTF ≈ 0.38x
+
+## Installation
+
+```bash
+pip install numpy scipy soundfile libsvm-official
+```
+
+Or install as a package:
+
+```bash
+git clone https://github.com/talker93/visqol-python.git
+cd visqol-python
+pip install -e .
+```
+
+## Quick Start
+
+### Python API
+
+```python
+from visqol import VisqolApi
+
+# Audio mode (default) - for music and general audio
+api = VisqolApi()
+api.create(mode="audio")
+result = api.measure("reference.wav", "degraded.wav")
+print(f"MOS-LQO: {result.moslqo:.4f}")
+
+# Speech mode - for speech signals
+api = VisqolApi()
+api.create(mode="speech")
+result = api.measure("ref_speech.wav", "deg_speech.wav")
+print(f"MOS-LQO: {result.moslqo:.4f}")
+```
+
+### Using NumPy Arrays
+
+```python
+import numpy as np
+import soundfile as sf
+from visqol import VisqolApi
+
+ref, sr = sf.read("reference.wav")
+deg, _  = sf.read("degraded.wav")
+
+api = VisqolApi()
+api.create(mode="audio")
+result = api.measure_from_arrays(ref, deg, sample_rate=sr)
+print(f"MOS-LQO: {result.moslqo:.4f}")
+```
+
+### Command Line
+
+```bash
+# Audio mode (default)
+python -m visqol -r reference.wav -d degraded.wav
+
+# Speech mode
+python -m visqol -r reference.wav -d degraded.wav --speech_mode
+
+# Verbose output (per-patch details)
+python -m visqol -r reference.wav -d degraded.wav -v
+```
+
+**CLI options:**
+
+| Flag | Description |
+|------|-------------|
+| `-r`, `--reference` | Path to reference WAV file (required) |
+| `-d`, `--degraded` | Path to degraded WAV file (required) |
+| `--speech_mode` | Use speech mode (16 kHz, polynomial mapping) |
+| `--model` | Custom SVR model file path (audio mode only) |
+| `--search_window` | Search window radius (default: 60) |
+| `--verbose`, `-v` | Show detailed per-patch results |
+
+## Output
+
+The `measure()` method returns a `SimilarityResult` object with:
+
+| Field | Description |
+|-------|-------------|
+| `moslqo` | MOS-LQO score (1.0 – 5.0) |
+| `vnsim` | Mean NSIM across all patches |
+| `fvnsim` | Per-frequency-band mean NSIM |
+| `fstdnsim` | Per-frequency-band std of NSIM |
+| `fvdegenergy` | Per-frequency-band degraded energy |
+| `patch_sims` | List of per-patch similarity details |
+
+## Modes
+
+### Audio Mode (default)
+- Target sample rate: **48 kHz**
+- 32 Gammatone frequency bands (50 Hz – 15 000 Hz)
+- Quality mapping: SVR (Support Vector Regression) model
+- Best for: music, environmental audio, codecs
+
+### Speech Mode
+- Target sample rate: **16 kHz**
+- 32 Gammatone frequency bands (50 Hz – 8 000 Hz)
+- Quality mapping: exponential polynomial fit
+- VAD (Voice Activity Detection) based patch selection
+- Best for: speech, VoIP, telephony
+
+## Performance
+
+Measured on Apple M-series, Python 3.13:
+
+| Mode | Avg RTF | Typical Time |
+|------|---------|-------------|
+| Audio (48 kHz) | **0.71x** | 7 – 12 s per file pair |
+| Speech (16 kHz) | **0.38x** | ~1 s per file pair |
+
+> RTF (Real-Time Factor) < 1.0 means faster than real-time.
+
+## Project Structure
+
+```
+visqol-python/
+├── visqol/                    # Main package
+│   ├── __init__.py            # Package exports
+│   ├── api.py                 # Public API
+│   ├── visqol_manager.py      # Pipeline orchestrator
+│   ├── visqol_core.py         # Core algorithm
+│   ├── audio_utils.py         # Audio I/O & SPL normalization
+│   ├── signal_utils.py        # Envelope, cross-correlation
+│   ├── analysis_window.py     # Hann window
+│   ├── gammatone.py           # ERB + Gammatone filterbank + spectrogram
+│   ├── patch_creator.py       # Patch creation (Image + VAD modes)
+│   ├── patch_selector.py      # DP-based optimal patch matching
+│   ├── alignment.py           # Global alignment via cross-correlation
+│   ├── nsim.py                # NSIM similarity metric
+│   ├── quality_mapper.py      # SVR & exponential quality mapping
+│   └── __main__.py            # CLI entry point
+├── model/                     # Bundled SVR model
+│   └── libsvm_nu_svr_model.txt
+├── tests/                     # Conformance tests
+│   ├── test_conformance.py
+│   └── test_quick.py
+├── setup.py
+├── requirements.txt
+├── LICENSE
+└── README.md
+```
+
+## Conformance Test Results
+
+Tested against the [official C++ ViSQOL v3.3.3](https://github.com/google/visqol) expected values:
+
+| Test Case | Mode | Expected MOS | Python MOS | Δ |
+|-----------|------|-------------|------------|---|
+| strauss_lp35 | Audio | 1.3889 | 1.3889 | 0.000000 |
+| steely_lp7 | Audio | 2.2502 | 2.2502 | 0.000000 |
+| sopr_256aac | Audio | 4.6823 | 4.6823 | 0.000000 |
+| ravel_128opus | Audio | 4.4651 | 4.4651 | 0.000000 |
+| moonlight_128aac | Audio | 4.6843 | 4.6843 | 0.000000 |
+| harpsichord_96mp3 | Audio | 4.2237 | 4.2237 | 0.000000 |
+| guitar_64aac | Audio | 4.3497 | 4.3497 | 0.000000 |
+| glock_48aac | Audio | 4.3325 | 4.3325 | 0.000000 |
+| contrabassoon_24aac | Audio | 2.3469 | 2.3468 | 0.000117 |
+| castanets_identity | Audio | 4.7321 | 4.7321 | 0.000000 |
+| speech_CA01 | Speech | 3.3745 | 3.3678 | 0.006715 |
+
+## References
+
+- [Google ViSQOL (C++)](https://github.com/google/visqol) — the original implementation this project is ported from
+- Hines, A., Gillen, E., Kelly, D., Skoglund, J., Kokaram, A., & Harte, N. (2015). *ViSQOLAudio: An Objective Audio Quality Metric for Low Bitrate Codecs.* The Journal of the Acoustical Society of America.
+- Chinen, M., Lim, F. S., Skoglund, J., Gureev, N., O'Gorman, F., & Hines, A. (2020). *ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric.* 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX).
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE) for details.
+
+This project is a Python port of [Google's ViSQOL](https://github.com/google/visqol), which is also licensed under Apache 2.0.

visqol_python-3.3.3/pyproject.toml

@@ -0,0 +1,53 @@
+[build-system]
+requires = ["setuptools>=64", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "visqol-python"
+version = "3.3.3"
+description = "ViSQOL - Virtual Speech Quality Objective Listener (Pure Python)"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.8"
+authors = [
+    {name = "Shan Jiang"},
+]
+keywords = [
+    "audio-quality", "speech-quality", "MOS", "PESQ", "POLQA",
+    "visqol", "objective-metric", "perceptual-quality",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Multimedia :: Sound/Audio :: Analysis",
+    "Topic :: Scientific/Engineering",
+]
+dependencies = [
+    "numpy>=1.20",
+    "scipy>=1.7",
+    "soundfile>=0.10",
+    "libsvm-official>=3.25",
+]
+
+[project.urls]
+Homepage = "https://github.com/talker93/visqol-python"
+"Bug Reports" = "https://github.com/talker93/visqol-python/issues"
+Source = "https://github.com/talker93/visqol-python"
+"Original C++" = "https://github.com/google/visqol"
+
+[project.scripts]
+visqol = "visqol.__main__:main"
+
+[tool.setuptools.packages.find]
+exclude = ["tests*"]
+
+[tool.setuptools.package-data]
+visqol = ["model/*.txt"]

visqol_python-3.3.3/requirements.txt

@@ -0,0 +1,4 @@
+numpy>=1.20
+scipy>=1.7
+soundfile>=0.10
+libsvm-official>=3.25

visqol_python-3.3.3/setup.cfg

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