clean up scripts, tweak subtitles

README.md

@@ -14,6 +14,14 @@ poetry install --no-root
 poetry self add poetry-plugin-shell
 poetry shell
 
+# Set up pre-commit hooks
+poetry run pre-commit install
+
+# Verify pre-commit hooks are working
+poetry run pre-commit run --all-files
+
+# See notebook_precommit.md for more details on how notebook outputs are automatically stripped
+
 # Install Jupyter kernel for this environment (needed for Jupyter notebooks)
 python -m ipykernel install --user --name=tgov-scraper --display-name="TGOV Scraper"
 ```
@@ -44,7 +52,7 @@ pytest -v
 - 'scripts`: one off scripts for downloading, conversions, etc
 - `tests/`: Test files
 - `notebooks/`: Jupyter notebooks for analysis and exploration
-- `data/`: output from notebooks 
+- `data/`: output from notebooks
 
 
 ## Running the transcription scripts

notebooks/vtt_subtitles.ipynb

@@ -70,17 +70,17 @@
     "\n",
     "# Import from the new subtitles module\n",
     "from src.subtitles import create_track, load_transcript\n",
-    "from src.models.subtitles import TrackFormat\n",
+    "from src.models.subtitles import SubtitleTrack\n",
     "\n",
     "# Path to the transcript file\n",
     "transcript_file = Path(\n",
     "    \"../data/transcripts/regular_council_meeting___2025_02_26.diarized.json\"\n",
     ")\n",
     "\n",
     "# Create VTT track\n",
-    "vtt_track = create_track(\n",
+    "vtt_track: SubtitleTrack = create_track(\n",
     "    transcript_data=transcript_file,\n",
-    "    track_format='vtt',\n",
+    "    format='vtt',\n",
     "    max_duration=5.0,\n",
     "    include_speaker_prefix=False,\n",
     ")\n",