forced-aligner-metrics 0.1.0__tar.gz

forced_aligner_metrics-0.1.0/.gitignore

@@ -0,0 +1,20 @@
+__pycache__/
+*.py[cod]
+*.pyo
+*.pyd
+*.egg-info/
+.venv/
+venv/
+.env
+.env.*
+.ipynb_checkpoints/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+.coverage.*
+htmlcov/
+dist/
+build/
+*.log
+.DS_Store

forced_aligner_metrics-0.1.0/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.

forced_aligner_metrics-0.1.0/PKG-INFO

@@ -0,0 +1,105 @@
+Metadata-Version: 2.4
+Name: forced-aligner-metrics
+Version: 0.1.0
+Summary: Reference-free forced alignment evaluation metrics
+Author-email: Mahesh Akavarapu <mahesh.akavarapu@gmail.com>
+License: Apache-2.0
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: transformers>=4.22.0
+Requires-Dist: scikit-learn>=1.1.0
+Requires-Dist: scipy>=1.7.2
+Requires-Dist: fastdtw>=0.3.4
+Provides-Extra: test
+Requires-Dist: torch; extra == "test"
+Requires-Dist: pytest>=7; extra == "test"
+Requires-Dist: datasets<=3.6.0; extra == "test"
+Requires-Dist: praat-parselmouth>=0.4.7; extra == "test"
+Requires-Dist: librosa>=0.11.0; extra == "test"
+Requires-Dist: soundfile>=0.13.1; extra == "test"
+Dynamic: license-file
+
+# Forced Alignment Evaluation Metrics: PCMI and WACS
+
+This repository contains the implementation of two reference-free forced alignment evaluation metrics:
+
+* **PCMI** (Phoneme-Cluster Mutual Information)
+* **WACS** (Word Acoustic Consistency Score)
+
+## Public API
+
+The package is intended to be used by importing the public interfaces from `forced_aligner_metrics`.
+
+### Configuration
+
+Use `ForcedAlignEvalConfig` to define evaluation behavior. Default config:
+
+```python
+from forced_aligner_metrics import ForcedAlignEvalConfig
+
+config = ForcedAlignEvalConfig(
+    model="facebook/mms-300m",
+    device="cuda",
+    layer_range=(15, 16),
+    batch_size=2,
+    samples_phon_eval=50,
+    max_frames=10_000,
+    n_clusters=50,
+    samples_word_eval=200,
+    max_words=200,
+    min_occ=3,
+    max_pairs=10,
+)
+```
+
+### Main evaluator
+
+Use `ForcedAlignEval` with:
+
+- `audios`: an iterator of audio arrays, each item is a numpy `array` sampled at **16kHz**:
+```python
+array([0.        , 0.        , 0.        , ..., 0.00074703, 0.00074613, 0.00078106])
+```
+- `intervals_iter`: an iterator of interval dictionaries, where each item is shaped like:
+
+```python
+{
+    "phones": [
+        {"text": "",  "start": 0.0, "end": 0.2},
+        {"text": "h", "start": 0.2, "end": 0.5},
+        {"text": "aI", "start": 0.5, "end": 1.0},
+    ],
+    "words": [
+        {"text": "",  "start": 0.0, "end": 0.2},
+        {"text": "Hi", "start": 0.2, "end": 1.0},
+    ],
+}
+```
+
+```python
+from forced_aligner_metrics import ForcedAlignEval, ForcedAlignEvalConfig
+
+config = ForcedAlignEvalConfig()
+evaluator = ForcedAlignEval(config)
+metrics = evaluator.compute_metrics(audios=audios, intervals_iter=intervals_iter)
+```
+
+The returned metrics dictionary contains the available scores for the evaluated sample. When a `phones` tier is present, the output includes the PCMI score under `pcmi_score`; when word-level embeddings are available, it includes the WACS score under `wacs_score`.
+
+
+## Installation for development
+
+Install the project in editable mode for development:
+
+```bash
+python -m pip install -e '.[test]'
+```
+
+## Tests
+
+Run the regression tests with:
+
+```bash
+python -m pytest
+```

forced_aligner_metrics-0.1.0/README.md

@@ -0,0 +1,83 @@
+# Forced Alignment Evaluation Metrics: PCMI and WACS
+
+This repository contains the implementation of two reference-free forced alignment evaluation metrics:
+
+* **PCMI** (Phoneme-Cluster Mutual Information)
+* **WACS** (Word Acoustic Consistency Score)
+
+## Public API
+
+The package is intended to be used by importing the public interfaces from `forced_aligner_metrics`.
+
+### Configuration
+
+Use `ForcedAlignEvalConfig` to define evaluation behavior. Default config:
+
+```python
+from forced_aligner_metrics import ForcedAlignEvalConfig
+
+config = ForcedAlignEvalConfig(
+    model="facebook/mms-300m",
+    device="cuda",
+    layer_range=(15, 16),
+    batch_size=2,
+    samples_phon_eval=50,
+    max_frames=10_000,
+    n_clusters=50,
+    samples_word_eval=200,
+    max_words=200,
+    min_occ=3,
+    max_pairs=10,
+)
+```
+
+### Main evaluator
+
+Use `ForcedAlignEval` with:
+
+- `audios`: an iterator of audio arrays, each item is a numpy `array` sampled at **16kHz**:
+```python
+array([0.        , 0.        , 0.        , ..., 0.00074703, 0.00074613, 0.00078106])
+```
+- `intervals_iter`: an iterator of interval dictionaries, where each item is shaped like:
+
+```python
+{
+    "phones": [
+        {"text": "",  "start": 0.0, "end": 0.2},
+        {"text": "h", "start": 0.2, "end": 0.5},
+        {"text": "aI", "start": 0.5, "end": 1.0},
+    ],
+    "words": [
+        {"text": "",  "start": 0.0, "end": 0.2},
+        {"text": "Hi", "start": 0.2, "end": 1.0},
+    ],
+}
+```
+
+```python
+from forced_aligner_metrics import ForcedAlignEval, ForcedAlignEvalConfig
+
+config = ForcedAlignEvalConfig()
+evaluator = ForcedAlignEval(config)
+metrics = evaluator.compute_metrics(audios=audios, intervals_iter=intervals_iter)
+```
+
+The returned metrics dictionary contains the available scores for the evaluated sample. When a `phones` tier is present, the output includes the PCMI score under `pcmi_score`; when word-level embeddings are available, it includes the WACS score under `wacs_score`.
+
+
+## Installation for development
+
+Install the project in editable mode for development:
+
+```bash
+python -m pip install -e '.[test]'
+```
+
+## Tests
+
+Run the regression tests with:
+
+```bash
+python -m pytest
+```

forced_aligner_metrics-0.1.0/pyproject.toml

@@ -0,0 +1,48 @@
+[build-system]
+requires = ["setuptools>=61", "setuptools-scm>=8", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "forced-aligner-metrics"
+dynamic = ["version"]
+authors = [{name = "Mahesh Akavarapu", email = "mahesh.akavarapu@gmail.com"},]
+description = "Reference-free forced alignment evaluation metrics"
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+dependencies = [
+  "transformers>=4.22.0",
+  "scikit-learn>=1.1.0",
+  "scipy>=1.7.2",
+  "fastdtw>=0.3.4",
+]
+
+[project.optional-dependencies]
+test = [
+  "torch",
+  "pytest>=7",
+  "datasets<=3.6.0",
+  "praat-parselmouth>=0.4.7",
+  "librosa>=0.11.0",
+  "soundfile>=0.13.1",
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools_scm]
+# Version is derived from the latest git tag (e.g. tag v0.2.0 -> version 0.2.0).
+# fallback_version is used only when no git metadata is available (e.g. building
+# from a source snapshot that isn't a git checkout).
+fallback_version = "0.0.0"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+markers = [
+  "integration: end-to-end tests that load models and datasets",
+  "slow: tests that are slow to run",
+]

forced_aligner_metrics-0.1.0/requirements.txt

@@ -0,0 +1,11 @@
+## Requirements tested for running tests only, core requirements are better tested for backward compatiblity
+torch
+transformers>=4.57.6
+scikit-learn>=1.6.1
+scipy>=1.15.2
+fastdtw>=0.3.4
+praat-parselmouth>=0.4.7
+pytest>=7.4.4
+datasets<=3.6.0
+librosa>=0.11.0
+soundfile>=0.13.1

forced_aligner_metrics-0.1.0/setup.cfg

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

forced_aligner_metrics-0.1.0/src/forced_aligner_metrics/__init__.py

@@ -0,0 +1,27 @@
+"""Public package interface for the forced alignment metrics project.
+
+Import the main public API directly from this module:
+
+    from forced_aligner_metrics import ForcedAlignEval, ForcedAlignEvalConfig
+
+Use ForcedAlignEvalConfig to configure the evaluator and ForcedAlignEval to
+run PCMI/WACS scoring from audio arrays and interval dictionaries.
+"""
+
+from importlib.metadata import PackageNotFoundError, version as _version
+
+from forced_aligner_metrics.eval_aligns import (
+    ForcedAlignEval,
+    ForcedAlignEvalConfig,
+)
+
+try:
+    __version__ = _version("forced-aligner-metrics")
+except PackageNotFoundError:  # running from a source tree without an install
+    __version__ = "0.0.0"
+
+__all__ = [
+    "ForcedAlignEval",
+    "ForcedAlignEvalConfig",
+    "__version__",
+]