lyrics-transcriber 0.66.0__tar.gz → 0.68.0__tar.gz

{lyrics_transcriber-0.66.0 → lyrics_transcriber-0.68.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lyrics-transcriber
-Version: 0.66.0
+Version: 0.68.0
 Summary: Automatically create synchronised lyrics files in ASS and MidiCo LRC formats with word-level timestamps, using Whisper and lyrics from Genius and Spotify
 License: MIT
 Author: Andrew Beveridge

{lyrics_transcriber-0.66.0 → lyrics_transcriber-0.68.0}/lyrics_transcriber/core/config.py

@@ -26,7 +26,7 @@ class OutputConfig:
     """Configuration for output generation."""
 
     output_styles_json: str
-    max_line_length: int = 36
+    default_max_line_length: int = 36
     styles: Dict[str, Any] = field(default_factory=dict)
     output_dir: Optional[str] = os.getcwd()
     cache_dir: str = os.getenv(

{lyrics_transcriber-0.66.0 → lyrics_transcriber-0.68.0}/lyrics_transcriber/core/controller.py

@@ -109,6 +109,9 @@ class LyricsTranscriber:
         # Initialize results
         self.results = LyricsControllerResult()
 
+        # Load styles early so lyrics providers can use them
+        self._load_styles()
+
         # Initialize components (with dependency injection)
         self.transcribers = transcribers or self._initialize_transcribers()
         self.lyrics_providers = lyrics_providers or self._initialize_lyrics_providers()
@@ -127,6 +130,20 @@ class LyricsTranscriber:
         if self.output_config.render_video:
             self.logger.info(f"    Video resolution: {self.output_config.video_resolution}")
 
+    def _load_styles(self) -> None:
+        """Load styles from JSON file if available."""
+        if self.output_config.output_styles_json and os.path.exists(self.output_config.output_styles_json):
+            try:
+                with open(self.output_config.output_styles_json, "r") as f:
+                    self.output_config.styles = json.load(f)
+                self.logger.debug(f"Loaded output styles from: {self.output_config.output_styles_json}")
+            except Exception as e:
+                self.logger.warning(f"Failed to load output styles file: {str(e)}")
+                self.output_config.styles = {}
+        else:
+            self.logger.debug("No styles JSON file provided or file does not exist")
+            self.output_config.styles = {}
+
     def _sanitize_filename(self, filename: str) -> str:
         """Replace or remove characters that are unsafe for filenames."""
         if not filename:
@@ -189,6 +206,10 @@ class LyricsTranscriber:
         """Initialize available lyrics providers."""
         providers = {}
 
+        # Get max_line_length from styles if available, otherwise use config default
+        max_line_length = self.output_config.styles.get("karaoke", {}).get("max_line_length", self.output_config.default_max_line_length)
+        self.logger.info(f"Using max_line_length for lyrics providers: {max_line_length}")
+
         # Create provider config with all necessary parameters
         provider_config = LyricsProviderConfig(
             genius_api_token=self.lyrics_config.genius_api_token,
@@ -197,6 +218,7 @@ class LyricsTranscriber:
             lyrics_file=self.lyrics_config.lyrics_file,
             cache_dir=self.output_config.cache_dir,
             audio_filepath=self.audio_filepath,
+            max_line_length=max_line_length,
         )
 
         if provider_config.lyrics_file and os.path.exists(provider_config.lyrics_file):

{lyrics_transcriber-0.66.0 → lyrics_transcriber-0.68.0}/lyrics_transcriber/correction/anchor_sequence.py

@@ -432,11 +432,12 @@ class AnchorSequenceFinder:
                     self.logger.info(f"🔍 ANCHOR SEARCH: ✅ All {len(async_results)} jobs submitted")
                     
                     # Collect results with individual timeouts
+                    batch_results = []
+                    batch_size = 10
+                    
                     for i, async_result in enumerate(async_results):
                         n_gram_length = n_gram_lengths[i]
                         try:
-                            self.logger.info(f"🔍 ANCHOR SEARCH: ⏳ Collecting result {i+1}/{len(async_results)} for n-gram length {n_gram_length}")
-                            
                             # Check remaining time for pool timeout (more lenient than overall timeout)
                             elapsed_time = time.time() - start_time
                             remaining_time = max(10, self.timeout_seconds - elapsed_time) if self.timeout_seconds > 0 else pool_timeout
@@ -449,12 +450,24 @@ class AnchorSequenceFinder:
                             result = async_result.get(timeout=individual_timeout)
                             results.append(result)
                             
-                            self.logger.info(f"🔍 ANCHOR SEARCH: ✅ Completed n-gram length {n_gram_length} ({i+1}/{len(n_gram_lengths)}) - found {len(result)} anchors")
+                            # Batch logging - collect info for batched logging
+                            batch_results.append((n_gram_length, len(result)))
+                            
+                            # Log progress every batch_size results or on the last result
+                            if (i + 1) % batch_size == 0 or (i + 1) == len(async_results):
+                                total_anchors_in_batch = sum(anchor_count for _, anchor_count in batch_results)
+                                n_gram_ranges = [str(ng) for ng, _ in batch_results]
+                                range_str = f"{n_gram_ranges[0]}-{n_gram_ranges[-1]}" if len(n_gram_ranges) > 1 else n_gram_ranges[0]
+                                self.logger.info(f"🔍 ANCHOR SEARCH: ✅ Completed n-gram lengths {range_str} ({i+1-len(batch_results)+1}-{i+1}/{len(async_results)}) - found {total_anchors_in_batch} anchors total")
+                                batch_results = []  # Reset batch
                             
                         except Exception as e:
                             self.logger.warning(f"🔍 ANCHOR SEARCH: ⚠️ n-gram length {n_gram_length} failed or timed out: {str(e)}")
                             results.append([])  # Add empty result to maintain order
                             
+                            # Add failed result to batch for logging
+                            batch_results.append((n_gram_length, 0))
+                            
                             # If we're running short on time, trigger fallback early
                             if self.timeout_seconds > 0 and (time.time() - start_time) > (self.timeout_seconds * 0.8):
                                 self.logger.warning(f"🔍 ANCHOR SEARCH: ⚠️ Approaching timeout limit, triggering early fallback")

{lyrics_transcriber-0.66.0 → lyrics_transcriber-0.68.0}/lyrics_transcriber/frontend/package.json

@@ -2,7 +2,7 @@
   "name": "lyrics-transcriber-frontend",
   "private": true,
   "homepage": "https://nomadkaraoke.github.io/lyrics-transcriber-frontend",
-  "version": "0.66.0",
+  "version": "0.68.0",
   "type": "module",
   "scripts": {
     "dev": "vite",

lyrics_transcriber-0.66.0/lyrics_transcriber/frontend/web_assets/assets/index-BMWgZ3MR.js → lyrics_transcriber-0.68.0/lyrics_transcriber/frontend/web_assets/assets/index-D7BQUJXK.js

@@ -38915,7 +38915,7 @@ const theme = createTheme({
   spacing: (factor) => `${0.6 * factor}rem`
   // Further reduced from 0.8 * factor
 });
-const version = "0.66.0";
+const version = "0.68.0";
 const packageJson = {
   version
 };
@@ -38926,4 +38926,4 @@ ReactDOM$1.createRoot(document.getElementById("root")).render(
     /* @__PURE__ */ jsxRuntimeExports.jsx(App, {})
   ] })
 );
-//# sourceMappingURL=index-BMWgZ3MR.js.map
+//# sourceMappingURL=index-D7BQUJXK.js.map