From 3663aff2664626642f6b0091f2bf615726e3a593 Mon Sep 17 00:00:00 2001
From: Andrew Beveridge <andrew@beveridge.uk>
Date: Tue, 28 Jan 2025 15:38:31 -0500
Subject: [PATCH] FIxed model downloadign

---
 .../correction/handlers/syllables_match.py    | 24 +++++++++++++++++--
 pyproject.toml                                |  2 +-
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/lyrics_transcriber/correction/handlers/syllables_match.py b/lyrics_transcriber/correction/handlers/syllables_match.py
index 04e2ee8..a4c611b 100644
--- a/lyrics_transcriber/correction/handlers/syllables_match.py
+++ b/lyrics_transcriber/correction/handlers/syllables_match.py
@@ -16,22 +16,42 @@ class SyllablesMatchHandler(GapCorrectionHandler):
     """Handles gaps where number of syllables in reference text matches number of syllables in transcription."""
 
     def __init__(self):
+        # Initialize logger first
+        self.logger = logging.getLogger(__name__)
+
         # Marking SpacySyllables as used to prevent unused import warning
         _ = SpacySyllables
+
         # Load spacy model with syllables pipeline
-        self.nlp = spacy.load("en_core_web_sm")
+        try:
+            self.nlp = spacy.load("en_core_web_sm")
+        except OSError:
+            self.logger.info("Language model 'en_core_web_sm' not found. Attempting to download...")
+            import subprocess
+
+            try:
+                subprocess.check_call(["python", "-m", "spacy", "download", "en_core_web_sm"])
+                self.nlp = spacy.load("en_core_web_sm")
+                self.logger.info("Successfully downloaded and loaded en_core_web_sm")
+            except subprocess.CalledProcessError as e:
+                raise OSError(
+                    "Language model 'en_core_web_sm' could not be downloaded. "
+                    "Please install it manually with: python -m spacy download en_core_web_sm"
+                ) from e
+
         # Add syllables component to pipeline if not already present
         if "syllables" not in self.nlp.pipe_names:
             self.nlp.add_pipe("syllables", after="tagger")
+
         # Initialize Pyphen for English
         self.dic = pyphen.Pyphen(lang="en_US")
+
         # Initialize NLTK's CMU dictionary
         try:
             self.cmudict = cmudict.dict()
         except LookupError:
             nltk.download("cmudict")
             self.cmudict = cmudict.dict()
-        self.logger = logging.getLogger(__name__)
 
     def _count_syllables_spacy(self, words: List[str]) -> int:
         """Count syllables using spacy_syllables."""
diff --git a/pyproject.toml b/pyproject.toml
index b8da60f..169c687 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "lyrics-transcriber"
-version = "0.34.0"
+version = "0.34.1"
 description = "Automatically create synchronised lyrics files in ASS and MidiCo LRC formats with word-level timestamps, using Whisper and lyrics from Genius and Spotify"
 authors = ["Andrew Beveridge <andrew@beveridge.uk>"]
 license = "MIT"