lyrics-transcriber 0.43.0__py3-none-any.whl → 0.44.0__py3-none-any.whl

lyrics_transcriber/frontend/src/theme.ts

@@ -0,0 +1,177 @@
+import { createTheme } from '@mui/material/styles';
+
+// Create a theme with smaller typography and spacing
+const theme = createTheme({
+  typography: {
+    // Scale down all typography by about 20%
+    fontSize: 14, // Default is 16
+    h1: {
+      fontSize: '2.5rem', // Default is ~3rem
+    },
+    h2: {
+      fontSize: '2rem', // Default is ~2.5rem
+    },
+    h3: {
+      fontSize: '1.5rem', // Default is ~1.75rem
+    },
+    h4: {
+      fontSize: '1.2rem', // Default is ~1.5rem
+      marginBottom: '0.5rem',
+    },
+    h5: {
+      fontSize: '1rem', // Default is ~1.25rem
+    },
+    h6: {
+      fontSize: '0.9rem', // Default is ~1.1rem
+      marginBottom: '0.5rem',
+    },
+    body1: {
+      fontSize: '0.85rem', // Default is ~1rem
+    },
+    body2: {
+      fontSize: '0.75rem', // Default is ~0.875rem
+    },
+    button: {
+      fontSize: '0.8rem', // Default is ~0.875rem
+    },
+    caption: {
+      fontSize: '0.7rem', // Default is ~0.75rem
+    },
+  },
+  components: {
+    MuiButton: {
+      styleOverrides: {
+        root: {
+          padding: '3px 10px', // Further reduced from 4px 12px
+          minHeight: '30px', // Further reduced from 32px
+        },
+        sizeSmall: {
+          padding: '1px 6px', // Further reduced from 2px 8px
+          minHeight: '24px', // Further reduced from 28px
+        },
+      },
+    },
+    MuiIconButton: {
+      styleOverrides: {
+        root: {
+          padding: '4px', // Further reduced from 6px
+        },
+        sizeSmall: {
+          padding: '2px', // Further reduced from 4px
+        },
+      },
+    },
+    MuiTextField: {
+      styleOverrides: {
+        root: {
+          '& .MuiInputBase-root': {
+            minHeight: '32px', // Further reduced from 36px
+          },
+        },
+      },
+    },
+    MuiDialog: {
+      styleOverrides: {
+        paper: {
+          padding: '8px', // Further reduced from 12px
+        },
+      },
+    },
+    MuiDialogTitle: {
+      styleOverrides: {
+        root: {
+          padding: '8px 12px', // Further reduced from 12px 16px
+        },
+      },
+    },
+    MuiDialogContent: {
+      styleOverrides: {
+        root: {
+          padding: '6px 12px', // Further reduced from 8px 16px
+        },
+      },
+    },
+    MuiDialogActions: {
+      styleOverrides: {
+        root: {
+          padding: '6px 12px', // Further reduced from 8px 16px
+        },
+      },
+    },
+    MuiPaper: {
+      styleOverrides: {
+        root: {
+          padding: '8px', // Further reduced from 12px
+        },
+      },
+    },
+    MuiList: {
+      styleOverrides: {
+        root: {
+          padding: '2px 0', // Further reduced from 4px 0
+        },
+      },
+    },
+    MuiListItem: {
+      styleOverrides: {
+        root: {
+          padding: '2px 8px', // Further reduced from 4px 12px
+        },
+      },
+    },
+    MuiTableCell: {
+      styleOverrides: {
+        root: {
+          padding: '4px 8px', // Further reduced from 8px 12px
+        },
+      },
+    },
+    MuiCard: {
+      styleOverrides: {
+        root: {
+          padding: '8px',
+        },
+      },
+    },
+    MuiCardContent: {
+      styleOverrides: {
+        root: {
+          padding: '8px',
+          '&:last-child': {
+            paddingBottom: '8px',
+          },
+        },
+      },
+    },
+    MuiCardHeader: {
+      styleOverrides: {
+        root: {
+          padding: '8px',
+        },
+      },
+    },
+    MuiCardActions: {
+      styleOverrides: {
+        root: {
+          padding: '4px 8px',
+        },
+      },
+    },
+    MuiGrid: {
+      styleOverrides: {
+        container: {
+          marginTop: '-4px',
+          marginLeft: '-4px',
+          width: 'calc(100% + 8px)',
+        },
+        item: {
+          paddingTop: '4px',
+          paddingLeft: '4px',
+        },
+      },
+    },
+  },
+  spacing: (factor: number) => `${0.6 * factor}rem`, // Further reduced from 0.8 * factor
+});
+
+export default theme; 

lyrics_transcriber/frontend/src/types.ts

@@ -136,4 +136,4 @@ export interface HighlightInfo {
     correction?: WordCorrection
 }
 
-export type InteractionMode = 'highlight' | 'details' | 'edit'
+export type InteractionMode = 'highlight' | 'edit'

lyrics_transcriber/frontend/tsconfig.tsbuildinfo

@@ -1 +1 @@
-{"root":["./src/app.tsx","./src/api.ts","./src/main.tsx","./src/types.ts","./src/validation.ts","./src/vite-env.d.ts","./src/components/audioplayer.tsx","./src/components/correctionmetrics.tsx","./src/components/detailsmodal.tsx","./src/components/editmodal.tsx","./src/components/fileupload.tsx","./src/components/header.tsx","./src/components/lyricsanalyzer.tsx","./src/components/modeselector.tsx","./src/components/previewvideosection.tsx","./src/components/referenceview.tsx","./src/components/reviewchangesmodal.tsx","./src/components/segmentdetailsmodal.tsx","./src/components/timelineeditor.tsx","./src/components/transcriptionview.tsx","./src/components/wordeditcontrols.tsx","./src/components/shared/constants.ts","./src/components/shared/styles.ts","./src/components/shared/types.ts","./src/components/shared/components/highlightedtext.tsx","./src/components/shared/components/sourceselector.tsx","./src/components/shared/components/word.tsx","./src/components/shared/hooks/usewordclick.ts","./src/components/shared/utils/keyboardhandlers.ts","./src/components/shared/utils/localstorage.ts","./src/components/shared/utils/referencelinecalculator.ts","./src/components/shared/utils/segmentoperations.ts","./src/components/shared/utils/wordutils.ts","./src/types/global.d.ts"],"version":"5.6.3"}
+{"root":["./src/app.tsx","./src/api.ts","./src/main.tsx","./src/theme.ts","./src/types.ts","./src/validation.ts","./src/vite-env.d.ts","./src/components/addlyricsmodal.tsx","./src/components/audioplayer.tsx","./src/components/correctionmetrics.tsx","./src/components/editmodal.tsx","./src/components/fileupload.tsx","./src/components/findreplacemodal.tsx","./src/components/globalsynceditor.tsx","./src/components/header.tsx","./src/components/lyricsanalyzer.tsx","./src/components/modeselector.tsx","./src/components/previewvideosection.tsx","./src/components/referenceview.tsx","./src/components/reviewchangesmodal.tsx","./src/components/segmentdetailsmodal.tsx","./src/components/timelineeditor.tsx","./src/components/transcriptionview.tsx","./src/components/worddivider.tsx","./src/components/shared/constants.ts","./src/components/shared/styles.ts","./src/components/shared/types.ts","./src/components/shared/components/highlightedtext.tsx","./src/components/shared/components/sourceselector.tsx","./src/components/shared/components/word.tsx","./src/components/shared/hooks/usewordclick.ts","./src/components/shared/utils/keyboardhandlers.ts","./src/components/shared/utils/localstorage.ts","./src/components/shared/utils/referencelinecalculator.ts","./src/components/shared/utils/segmentoperations.ts","./src/components/shared/utils/wordutils.ts","./src/hooks/usemanualsync.ts","./src/types/global.d.ts"],"version":"5.6.3"}

lyrics_transcriber/lyrics/base_lyrics_provider.py

@@ -47,14 +47,14 @@ class BaseLyricsProvider(ABC):
         converted_cache_path = self._get_cache_path(cache_key, "converted")
         converted_data = self._load_from_cache(converted_cache_path)
         if converted_data:
-            self.logger.info(f"Using cached converted lyrics for {artist} - {title}")
+            self.logger.info(f"Using cached converted lyrics for {artist} - {title} from file: {converted_cache_path}")
             return LyricsData.from_dict(converted_data)
 
         # Check raw cache next
         raw_cache_path = self._get_cache_path(cache_key, "raw")
         raw_data = self._load_from_cache(raw_cache_path)
         if raw_data:
-            self.logger.info(f"Using cached raw lyrics for {artist} - {title}")
+            self.logger.info(f"Using cached raw lyrics for {artist} - {title} from file: {raw_cache_path}")
             converted_result = self._convert_result_format(raw_data)
             self._save_to_cache(converted_cache_path, converted_result.to_dict())
             return converted_result

lyrics_transcriber/lyrics/user_input_provider.py

@@ -0,0 +1,44 @@
+from typing import Optional, Dict, Any
+from lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
+from lyrics_transcriber.types import LyricsData, LyricsMetadata
+
+
+class UserInputProvider(BaseLyricsProvider):
+    """Provider for manually input lyrics text."""
+
+    def __init__(self, lyrics_text: str, source_name: str, metadata: Dict[str, Any], *args, **kwargs):
+        """Initialize with the user's input text."""
+        super().__init__(LyricsProviderConfig(), *args, **kwargs)
+        self.lyrics_text = lyrics_text
+        self.source_name = source_name
+        self.input_metadata = metadata
+
+    def _fetch_data_from_source(self, artist: str, title: str) -> Optional[Dict[str, Any]]:
+        """Return the user's input text as raw data."""
+        return {"text": self.lyrics_text, "metadata": self.input_metadata}
+
+    def _convert_result_format(self, raw_data: Dict[str, Any]) -> LyricsData:
+        """Convert the raw text into LyricsData format."""
+        # Create segments with words from the text
+        segments = self._create_segments_with_words(raw_data["text"])
+
+        # Create metadata
+        metadata = LyricsMetadata(
+            source=self.source_name,
+            track_name=raw_data["metadata"].get("title", ""),
+            artist_names=raw_data["metadata"].get("artist", ""),
+            is_synced=False,
+            lyrics_provider="manual",
+            lyrics_provider_id="",
+            album_name=None,
+            duration_ms=None,
+            explicit=None,
+            language=None,
+            provider_metadata={},
+        )
+
+        return LyricsData(segments=segments, metadata=metadata, source=self.source_name)
+
+    def get_name(self) -> str:
+        """Return the provider name."""
+        return "UserInput"

lyrics_transcriber/output/generator.py

@@ -37,6 +37,7 @@ class OutputGenerator:
         self,
         config: OutputConfig,
         logger: Optional[logging.Logger] = None,
+        preview_mode: bool = False,
     ):
         """
         Initialize OutputGenerator with configuration.
@@ -44,20 +45,12 @@ class OutputGenerator:
         Args:
             config: OutputConfig instance with required paths and settings
             logger: Optional logger instance
+            preview_mode: Boolean indicating if the generator is in preview mode
         """
         self.config = config
         self.logger = logger or logging.getLogger(__name__)
 
-        self.logger.debug(f"Initializing OutputGenerator with config: {self.config}")
-
-        # Set video resolution parameters
-        self.video_resolution_num, self.font_size, self.line_height = self._get_video_params(self.config.video_resolution)
-
-        self.segment_resizer = SegmentResizer(max_line_length=self.config.max_line_length, logger=self.logger)
-
-        # Initialize generators
-        self.plain_text = PlainTextGenerator(self.config.output_dir, self.logger)
-        self.lyrics_file = LyricsFileGenerator(self.config.output_dir, self.logger)
+        self.logger.info(f"Initializing OutputGenerator with config: {self.config}")
 
         if self.config.render_video or self.config.generate_cdg:
             # Load output styles from JSON
@@ -68,10 +61,46 @@ class OutputGenerator:
             except Exception as e:
                 raise ValueError(f"Failed to load output styles file: {str(e)}")
 
+        # Set video resolution parameters
+        self.video_resolution_num, self.font_size, self.line_height = self._get_video_params(self.config.video_resolution)
+        self.logger.info(f"Video resolution: {self.video_resolution_num}, font size: {self.font_size}, line height: {self.line_height}")
+
+        self.segment_resizer = SegmentResizer(max_line_length=self.config.max_line_length, logger=self.logger)
+
+        # Initialize generators
+        self.plain_text = PlainTextGenerator(self.config.output_dir, self.logger)
+        self.lyrics_file = LyricsFileGenerator(self.config.output_dir, self.logger)
+
         if self.config.generate_cdg:
             self.cdg = CDGGenerator(self.config.output_dir, self.logger)
 
+        self.preview_mode = preview_mode
         if self.config.render_video:
+            # Apply preview mode scaling if needed
+            if self.preview_mode:
+                # Scale down from 4K (2160p) to 360p - factor of 1/6
+                scale_factor = 1 / 6
+
+                # Scale down top padding for preview if it exists
+                if "karaoke" in self.config.styles and "top_padding" in self.config.styles["karaoke"]:
+                    self.logger.info(f"Preview mode: Found top_padding: {self.config.styles['karaoke']['top_padding']}")
+                    original_padding = self.config.styles["karaoke"]["top_padding"]
+                    if original_padding is not None:
+                        # Scale down from 4K (2160p) to 360p - factor of 1/6
+                        self.config.styles["karaoke"]["top_padding"] = original_padding * scale_factor
+                        self.logger.info(f"Preview mode: Scaled down top_padding to: {self.config.styles['karaoke']['top_padding']}")
+
+                # Scale down font size for preview if it exists
+                if "karaoke" in self.config.styles and "font_size" in self.config.styles["karaoke"]:
+                    self.logger.info(f"Preview mode: Found font_size: {self.config.styles['karaoke']['font_size']}")
+                    original_font_size = self.config.styles["karaoke"]["font_size"]
+                    if original_font_size is not None:
+                        # Scale down from 4K (2160p) to 360p - factor of 1/6
+                        self.font_size = original_font_size * scale_factor
+                        self.config.styles["karaoke"]["font_size"] = self.font_size
+                        self.logger.info(f"Preview mode: Scaled down font_size to: {self.font_size}")
+
+            # Initialize subtitle generator with potentially scaled values
             self.subtitle = SubtitlesGenerator(
                 output_dir=self.config.output_dir,
                 video_resolution=self.video_resolution_num,
@@ -102,7 +131,6 @@ class OutputGenerator:
         audio_filepath: str,
         artist: Optional[str] = None,
         title: Optional[str] = None,
-        preview_mode: bool = False,
     ) -> OutputPaths:
         """Generate all requested output formats."""
         outputs = OutputPaths()
@@ -116,7 +144,7 @@ class OutputGenerator:
                 transcription_corrected.resized_segments = resized_segments
 
                 # For preview, we only need to generate ASS and video
-                if preview_mode:
+                if self.preview_mode:
                     # Generate ASS subtitles for preview
                     outputs.ass = self.subtitle.generate_ass(transcription_corrected.resized_segments, output_prefix, audio_filepath)
 

lyrics_transcriber/output/video.py

@@ -63,8 +63,12 @@ class VideoGenerator:
             raise FileNotFoundError(f"Audio file not found: {audio_path}")
 
         try:
-            # Create a temporary copy of the ASS file with a safe filename
-            temp_ass_path = os.path.join(self.cache_dir, "temp_subtitles.ass")
+            # Create a temporary copy of the ASS file with a unique filename
+            import time
+
+            safe_prefix = "".join(c if c.isalnum() else "_" for c in output_prefix)
+            timestamp = int(time.time() * 1000)
+            temp_ass_path = os.path.join(self.cache_dir, f"temp_subtitles_{safe_prefix}_{timestamp}.ass")
             import shutil
 
             shutil.copy2(ass_path, temp_ass_path)
@@ -75,13 +79,14 @@ class VideoGenerator:
             self.logger.info(f"Video generated: {output_path}")
 
             # Clean up temporary file
-            os.remove(temp_ass_path)
+            if os.path.exists(temp_ass_path):
+                os.remove(temp_ass_path)
             return output_path
 
         except Exception as e:
             self.logger.error(f"Failed to generate video: {str(e)}")
             # Clean up temporary file in case of error
-            if "temp_ass_path" in locals():
+            if "temp_ass_path" in locals() and os.path.exists(temp_ass_path):
                 try:
                     os.remove(temp_ass_path)
                 except:
@@ -109,8 +114,12 @@ class VideoGenerator:
             raise FileNotFoundError(f"Audio file not found: {audio_path}")
 
         try:
-            # Create a temporary copy of the ASS file with a safe filename
-            temp_ass_path = os.path.join(self.cache_dir, "temp_preview_subtitles.ass")
+            # Create a temporary copy of the ASS file with a unique filename
+            import time
+
+            safe_prefix = "".join(c if c.isalnum() else "_" for c in output_prefix)
+            timestamp = int(time.time() * 1000)
+            temp_ass_path = os.path.join(self.cache_dir, f"temp_preview_subtitles_{safe_prefix}_{timestamp}.ass")
             import shutil
 
             shutil.copy2(ass_path, temp_ass_path)
@@ -121,13 +130,14 @@ class VideoGenerator:
             self.logger.info(f"Preview video generated: {output_path}")
 
             # Clean up temporary file
-            os.remove(temp_ass_path)
+            if os.path.exists(temp_ass_path):
+                os.remove(temp_ass_path)
             return output_path
 
         except Exception as e:
             self.logger.error(f"Failed to generate preview video: {str(e)}")
             # Clean up temporary file in case of error
-            if "temp_ass_path" in locals():
+            if "temp_ass_path" in locals() and os.path.exists(temp_ass_path):
                 try:
                     os.remove(temp_ass_path)
                 except: