Colab-ready GPU bootstrap and validation for ArtP and DArtP

.github/workflows/tests.yml

@@ -7,6 +7,34 @@ on:
     branches: ["**"]
 
 jobs:
+  dependency-resolution:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Resolve dependencies without GitHub credentials
+        env:
+          GIT_TERMINAL_PROMPT: "0"
+        run: |
+          python -m venv /tmp/pathbench-clean
+          /tmp/pathbench-clean/bin/python -m pip install --upgrade pip
+          /tmp/pathbench-clean/bin/python -m pip install \
+            --dry-run --ignore-installed --report /tmp/install-report.json .
+          /tmp/pathbench-clean/bin/python - <<'PY'
+          import json
+          from pathlib import Path
+
+          report = json.loads(Path("/tmp/install-report.json").read_text())
+          urls = [item["download_info"]["url"] for item in report["install"]]
+          vcs_urls = [url for url in urls if url.startswith("git+") or "github.com" in url]
+          assert not vcs_urls, f"VCS/GitHub dependencies remain: {vcs_urls}"
+          PY
+
   test:
     runs-on: ubuntu-latest
     strategy:

docs/installation.rst

@@ -39,5 +39,8 @@ Without sudo access, a containerised environment such as Docker is recommended.
 
 .. note::
 
-   PathBench cannot be published to PyPI because it depends on Git-hosted forks
-   of ``phonemizer`` and ``pyctcdecode``.
+   PathBench's Python dependencies are available as versioned package-index
+   releases, including ``phonemizer-fork==3.3.2`` and
+   ``pyctcdecode==0.5.0``. Installing them does not require GitHub credentials.
+   The ``espeak-ng`` shared library remains a separate system dependency; use
+   the revision documented in the project README for reproducible IPA output.

pyproject.toml

@@ -50,8 +50,10 @@ dependencies = [
     "transformers",
     "dtw-python",
     "jiwer",
-    "phonemizer-fork @ git+https://github.com/thewh1teagle/phonemizer-fork.git",
-    "pyctcdecode @ git+https://github.com/kensho-technologies/pyctcdecode.git",
+    # PyPI release of the fork; it continues to expose the ``phonemizer`` API.
+    "phonemizer-fork==3.3.2",
+    # Keep every runtime dependency installable without VCS/GitHub access.
+    "pyctcdecode==0.5.0",
     "praat-parselmouth>=0.4.4",
     "scikit-learn",
 ]