fix: make lyrics_transcriber a subpackage of karaoke_gen (#299)

## Summary
Fixes the deployment failure from PR #297 by making lyrics_transcriber a
proper subpackage of karaoke_gen instead of a separate vendored library.

### Changes
- Move `libs/lyrics_transcriber/` to `karaoke_gen/lyrics_transcriber/`
- Update all imports from `from lyrics_transcriber.X` to `from
karaoke_gen.lyrics_transcriber.X`
- Simplify Dockerfile (no separate `libs/` COPY needed)
- Update pyproject.toml to remove separate package entry
- Update test mocks and logger names

### Why this is better
- Cleaner project structure - one package containing everything
- Simpler Dockerfile - just COPY karaoke_gen/
- No confusion about vendored vs internal code

## Test plan
- [x] `poetry install` succeeds
- [x] All imports work correctly
- [x] All 2614 tests pass
- [ ] Backend deployment succeeds

@coderabbitai ignore

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Andrew Beveridge ☄️andClaude Opus 4.5 authored and GitHub committed 2026-01-19 16:53:34 +00:00
1 parent f3ee9e05f3
commit 404c6e6133
176 files changed
+269 -264

No files matched your search

@@ -57,7 +57,7 @@ karaoke-gen/
1. **`libs/`** - Clear convention for vendored/embedded libraries, separate from main codebase
2. **Single level** - `lyrics_transcriber` directly under `libs/`, not nested (no `libs/lyrics_transcriber/lyrics_transcriber/`)
3. **Clean imports** - `from lyrics_transcriber.core import ...` continues to work with proper Poetry config
3. **Clean imports** - `from karaoke_gen.lyrics_transcriber.core import ...` continues to work with proper Poetry config
### pyproject.toml Changes
@@ -132,7 +132,7 @@ From current `lyrics_transcriber_temp/`:
7. [ ] Remove `lyrics_transcriber_temp/` directory (with all its extra files)
8. [ ] Update `pyproject.toml` packages and include paths
9. [ ] Update the one script that references `lyrics_transcriber_temp` directly:
- `scripts/benchmark_encoding.py` line 232: change `from lyrics_transcriber_temp.lyrics_transcriber.output.video` to `from lyrics_transcriber.output.video`
- `scripts/benchmark_encoding.py` line 232: change `from lyrics_transcriber_temp.lyrics_transcriber.output.video` to `from karaoke_gen.lyrics_transcriber.output.video`
### Phase 3: Verify and Test
@@ -140,9 +140,9 @@ From current `lyrics_transcriber_temp/`:
11. [ ] Run `make test` to ensure all tests pass
12. [ ] Verify imports work:
```python
from lyrics_transcriber.core.controller import LyricsControllerResult
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.types import CorrectionResult
from karaoke_gen.lyrics_transcriber.core.controller import LyricsControllerResult
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.types import CorrectionResult
```
### Phase 4: Handle Tests from lyrics_transcriber
@@ -199,6 +199,6 @@ If issues arise:
## Notes
- The import paths like `from lyrics_transcriber.core import ...` will continue to work unchanged
- The import paths like `from karaoke_gen.lyrics_transcriber.core import ...` will continue to work unchanged
- Only the internal project structure changes, not the API
- This is primarily a cleanup/organization task with some external repo admin work
+2 -3
View File
@@ -22,10 +22,9 @@ WORKDIR /app
COPY backend /app/backend
# Copy and reinstall karaoke_gen from local source
# This ensures new modules (like style_loader.py) are included without rebuilding base image
# Note: lyrics_transcriber is vendored in lyrics_transcriber_temp/ and bundled via pyproject.toml
# This ensures new modules are included without rebuilding base image
# Note: lyrics_transcriber is now a subpackage of karaoke_gen
COPY karaoke_gen /app/karaoke_gen
COPY lyrics_transcriber_temp /app/lyrics_transcriber_temp
COPY pyproject.toml README.md LICENSE /app/
RUN pip install --no-cache-dir -e .
+3 -3
View File
@@ -33,9 +33,9 @@ from backend.services.auth_service import UserType
from backend.config import get_settings
# LyricsTranscriber imports for preview generation
from lyrics_transcriber.types import CorrectionResult
from lyrics_transcriber.core.config import OutputConfig
from lyrics_transcriber.correction.operations import CorrectionOperations
from karaoke_gen.lyrics_transcriber.types import CorrectionResult
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig
from karaoke_gen.lyrics_transcriber.correction.operations import CorrectionOperations
# Import from the unified style loader
from karaoke_gen.style_loader import load_styles_from_gcs
+1 -1
View File
@@ -120,7 +120,7 @@ class PackagingService:
)
self.logger.info("Generating CDG and MP3 files")
from lyrics_transcriber.output.cdg import CDGGenerator
from karaoke_gen.lyrics_transcriber.output.cdg import CDGGenerator
output_dir = os.path.dirname(output_zip_path) or os.getcwd()
generator = CDGGenerator(output_dir=output_dir, logger=self.logger)
+1 -1
View File
@@ -201,7 +201,7 @@ class TestPackagingServiceCDGPackage:
assert result[1] == mp3_file
assert result[2] == cdg_file
@patch("lyrics_transcriber.output.cdg.CDGGenerator")
@patch("karaoke_gen.lyrics_transcriber.output.cdg.CDGGenerator")
def test_create_cdg_package_with_generator(self, mock_cdg_generator_class):
"""Test CDG package creation using CDGGenerator."""
with tempfile.TemporaryDirectory() as tmpdir:
+1 -1
View File
@@ -204,7 +204,7 @@ class TestAddLyricsEndpoint:
def test_add_lyrics_uses_correction_operations(self):
"""Verify CorrectionOperations.add_lyrics_source is available."""
from lyrics_transcriber.correction.operations import CorrectionOperations
from karaoke_gen.lyrics_transcriber.correction.operations import CorrectionOperations
# The method should exist
assert hasattr(CorrectionOperations, 'add_lyrics_source')
+2 -2
View File
@@ -560,7 +560,7 @@ class TestRenderVideoWorkerCountdownPadding:
def test_countdown_processor_has_process_method(self):
"""Test that CountdownProcessor has the process method (main API)."""
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
from karaoke_gen.lyrics_transcriber.output.countdown_processor import CountdownProcessor
countdown_processor = CountdownProcessor(cache_dir="/tmp")
assert hasattr(countdown_processor, 'process')
@@ -568,7 +568,7 @@ class TestRenderVideoWorkerCountdownPadding:
def test_countdown_processor_constants(self):
"""Test that CountdownProcessor has expected constants."""
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
from karaoke_gen.lyrics_transcriber.output.countdown_processor import CountdownProcessor
# Verify the constants exist (these control countdown behavior)
assert hasattr(CountdownProcessor, 'COUNTDOWN_TEXT')
+8 -8
View File
@@ -36,10 +36,10 @@ from backend.workers.worker_logging import create_job_logger, setup_job_logging,
from backend.services.tracing import job_span, add_span_event, add_span_attribute
# Import from lyrics_transcriber (submodule)
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
from lyrics_transcriber.types import CorrectionResult
from lyrics_transcriber.core.config import OutputConfig
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.output.countdown_processor import CountdownProcessor
from karaoke_gen.lyrics_transcriber.types import CorrectionResult
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig
# Import from the unified style loader
from karaoke_gen.style_loader import load_styles_from_gcs
@@ -51,10 +51,10 @@ logger = logging.getLogger(__name__)
# Loggers to capture for render video worker
RENDER_VIDEO_WORKER_LOGGERS = [
"lyrics_transcriber.output",
"lyrics_transcriber.output.generator",
"lyrics_transcriber.output.video",
"lyrics_transcriber.output.ass",
"karaoke_gen.lyrics_transcriber.output",
"karaoke_gen.lyrics_transcriber.output.generator",
"karaoke_gen.lyrics_transcriber.output.video",
"karaoke_gen.lyrics_transcriber.output.ass",
]
+3 -3
View File
@@ -65,7 +65,7 @@ class JobLogHandler(logging.Handler):
lyrics_logger.addHandler(handler)
# Also capture logs from lyrics_transcriber package itself
lt_logger = logging.getLogger("lyrics_transcriber")
lt_logger = logging.getLogger("karaoke_gen.lyrics_transcriber")
lt_logger.addHandler(handler)
"""
@@ -235,7 +235,7 @@ def setup_job_logging(job_id: str, worker_name: str, *logger_names: str) -> JobL
Args:
job_id: Job ID
worker_name: Worker name
*logger_names: Names of loggers to capture (e.g., "lyrics_transcriber", "karaoke_gen")
*logger_names: Names of loggers to capture (e.g., "karaoke_gen.lyrics_transcriber", "karaoke_gen")
Returns:
The JobLogHandler (can be removed later if needed)
@@ -246,7 +246,7 @@ def setup_job_logging(job_id: str, worker_name: str, *logger_names: str) -> JobL
job_id,
"lyrics",
"karaoke_gen.lyrics_processor",
"lyrics_transcriber", # Capture LyricsTranscriber logs
"karaoke_gen.lyrics_transcriber", # Capture LyricsTranscriber logs
)
# IMPORTANT: Use job_logging_context for proper isolation
+1 -1
View File
@@ -265,7 +265,7 @@ gcloud logging read 'resource.type="cloud_run_revision" "ANCHOR SEARCH: Progress
When adding new operations that may need investigation:
```python
from lyrics_transcriber.utils.tracing import create_span, add_span_attribute
from karaoke_gen.lyrics_transcriber.utils.tracing import create_span, add_span_attribute
with create_span("operation_name", {"initial": "attributes"}) as span:
# ... do work ...
+2 -2
View File
@@ -285,7 +285,7 @@ async def process_audio_separation_task(job_id: str):
```python
# backend/workers/lyrics_worker.py
from karaoke_gen.lyrics_processor import LyricsProcessor
from lyrics_transcriber.transcriber import LyricsTranscriber
from karaoke_gen.lyrics_transcriber.transcriber import LyricsTranscriber
import os
async def process_lyrics_transcription_task(job_id: str):
@@ -735,7 +735,7 @@ async def encode_videos_task(job_id: str):
**Implementation:**
```python
# backend/workers/packaging_worker.py
from lyrics_transcriber.output.cdg import CDGGenerator
from karaoke_gen.lyrics_transcriber.output.cdg import CDGGenerator
from lyrics_converter import convert_lrc_to_txt
async def generate_cdg_package(job_id: str, work_dir: str):
+3 -3
View File
@@ -246,9 +246,9 @@ import logging
import tempfile
from typing import Optional
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.correction.corrector import CorrectionResult
from lyrics_transcriber.core.config import OutputConfig
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.correction.corrector import CorrectionResult
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig
from backend.services.job_manager import job_manager
from backend.services.storage_service import storage
@@ -175,8 +175,8 @@ config = LyricsTranscriberConfig(
**Key Insight:** Uses `OutputGenerator` from LyricsTranscriber library:
```python
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.correction.corrector import CorrectionResult
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.correction.corrector import CorrectionResult
# Load corrected data (from human review)
correction_result = CorrectionResult.from_dict(corrections_data)
@@ -382,9 +382,9 @@ POST /api/jobs/{job_id}/select-instrumental
### Example: Using OutputGenerator
```python
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.correction.corrector import CorrectionResult
from lyrics_transcriber.core.config import OutputConfig
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.correction.corrector import CorrectionResult
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig
# 1. Load corrected data from GCS (after human review)
corrections_data = download_json_from_gcs(f"jobs/{job_id}/corrections_updated.json")
@@ -181,7 +181,7 @@ You can also detect from LRC files:
To disable countdown for a specific transcription:
```python
from lyrics_transcriber.core.config import OutputConfig
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig
output_config = OutputConfig(
# ... other options
+1 -1
View File
@@ -21,7 +21,7 @@ yarn dev # Starts on port 5173
# Terminal 2: Start LyricsTranscriber backend (for API)
# This serves the review API on port 8767
poetry run python -c "from lyrics_transcriber.review.server import ReviewServer; ..."
poetry run python -c "from karaoke_gen.lyrics_transcriber.review.server import ReviewServer; ..."
# Terminal 3: Run the test
cd frontend
@@ -19,7 +19,7 @@ import time
from google.oauth2.credentials import Credentials
import base64
from email.mime.text import MIMEText
from lyrics_transcriber.output.cdg import CDGGenerator
from karaoke_gen.lyrics_transcriber.output.cdg import CDGGenerator
from ..utils import sanitize_filename
+4 -4
View File
@@ -32,10 +32,10 @@ from .video_background_processor import VideoBackgroundProcessor
from .audio_fetcher import create_audio_fetcher, AudioFetcherError, NoResultsError, UserCancelledError
# Import lyrics_transcriber components for post-review countdown and video rendering
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.types import CorrectionResult
from lyrics_transcriber.core.config import OutputConfig as LyricsOutputConfig
from karaoke_gen.lyrics_transcriber.output.countdown_processor import CountdownProcessor
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.types import CorrectionResult
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig as LyricsOutputConfig
class KaraokePrep:
+2 -2
View File
@@ -4,8 +4,8 @@ import logging
import shutil
import json
from typing import Optional
from lyrics_transcriber import LyricsTranscriber, OutputConfig, TranscriberConfig, LyricsConfig
from lyrics_transcriber.core.controller import LyricsControllerResult
from karaoke_gen.lyrics_transcriber import LyricsTranscriber, OutputConfig, TranscriberConfig, LyricsConfig
from karaoke_gen.lyrics_transcriber.core.controller import LyricsControllerResult
from dotenv import load_dotenv
from .utils import sanitize_filename
@@ -1,5 +1,5 @@
from lyrics_transcriber.core.config import TranscriberConfig, LyricsConfig, OutputConfig
from lyrics_transcriber.core.controller import LyricsTranscriber
from karaoke_gen.lyrics_transcriber.core.config import TranscriberConfig, LyricsConfig, OutputConfig
from karaoke_gen.lyrics_transcriber.core.controller import LyricsTranscriber
from importlib.metadata import version, PackageNotFoundError
try:
@@ -11,8 +11,8 @@ from typing import Dict
from importlib.metadata import version
from dotenv import load_dotenv
from lyrics_transcriber import LyricsTranscriber
from lyrics_transcriber.core.controller import TranscriberConfig, LyricsConfig, OutputConfig
from karaoke_gen.lyrics_transcriber import LyricsTranscriber
from karaoke_gen.lyrics_transcriber.core.controller import TranscriberConfig, LyricsConfig, OutputConfig
def create_arg_parser() -> argparse.ArgumentParser:
@@ -3,20 +3,20 @@ import logging
import json
from dataclasses import dataclass, field
from typing import Dict, Optional, List
from lyrics_transcriber.types import LyricsData, TranscriptionResult, CorrectionResult
from lyrics_transcriber.transcribers.base_transcriber import BaseTranscriber
from lyrics_transcriber.transcribers.audioshake import AudioShakeTranscriber, AudioShakeConfig
from lyrics_transcriber.transcribers.whisper import WhisperTranscriber, WhisperConfig
from lyrics_transcriber.transcribers.local_whisper import LocalWhisperTranscriber, LocalWhisperConfig
from lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from lyrics_transcriber.lyrics.genius import GeniusProvider
from lyrics_transcriber.lyrics.spotify import SpotifyProvider
from lyrics_transcriber.lyrics.musixmatch import MusixmatchProvider
from lyrics_transcriber.lyrics.lrclib import LRCLIBProvider
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.correction.corrector import LyricsCorrector
from lyrics_transcriber.core.config import TranscriberConfig, LyricsConfig, OutputConfig
from lyrics_transcriber.lyrics.file_provider import FileProvider
from karaoke_gen.lyrics_transcriber.types import LyricsData, TranscriptionResult, CorrectionResult
from karaoke_gen.lyrics_transcriber.transcribers.base_transcriber import BaseTranscriber
from karaoke_gen.lyrics_transcriber.transcribers.audioshake import AudioShakeTranscriber, AudioShakeConfig
from karaoke_gen.lyrics_transcriber.transcribers.whisper import WhisperTranscriber, WhisperConfig
from karaoke_gen.lyrics_transcriber.transcribers.local_whisper import LocalWhisperTranscriber, LocalWhisperConfig
from karaoke_gen.lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from karaoke_gen.lyrics_transcriber.lyrics.genius import GeniusProvider
from karaoke_gen.lyrics_transcriber.lyrics.spotify import SpotifyProvider
from karaoke_gen.lyrics_transcriber.lyrics.musixmatch import MusixmatchProvider
from karaoke_gen.lyrics_transcriber.lyrics.lrclib import LRCLIBProvider
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.correction.corrector import LyricsCorrector
from karaoke_gen.lyrics_transcriber.core.config import TranscriberConfig, LyricsConfig, OutputConfig
from karaoke_gen.lyrics_transcriber.lyrics.file_provider import FileProvider
@dataclass
@@ -301,7 +301,7 @@ class LyricsTranscriber:
# Debug: Log package version and environment variables
try:
import lyrics_transcriber
from karaoke_gen import lyrics_transcriber
package_version = getattr(lyrics_transcriber, '__version__', 'unknown')
self.logger.info(f"LyricsTranscriber package version: {package_version}")
except Exception as e:
@@ -345,7 +345,7 @@ class LyricsTranscriber:
# This is important because the video needs to use padded audio to sync
# with the countdown-adjusted timestamps in the ASS subtitles
if self.output_config.add_countdown:
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
from karaoke_gen.lyrics_transcriber.output.countdown_processor import CountdownProcessor
countdown_processor = CountdownProcessor(
cache_dir=self.output_config.cache_dir,
@@ -572,7 +572,7 @@ class LyricsTranscriber:
# Add human review step (moved outside the else block)
if self.output_config.enable_review:
from lyrics_transcriber.review.server import ReviewServer
from karaoke_gen.lyrics_transcriber.review.server import ReviewServer
self.logger.info("Starting human review process")
@@ -590,7 +590,7 @@ class LyricsTranscriber:
# Add countdown intro if enabled and needed (after review, before output generation)
if self.output_config.add_countdown and self.results.transcription_corrected:
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
from karaoke_gen.lyrics_transcriber.output.countdown_processor import CountdownProcessor
self.logger.info("Processing countdown intro (if needed)")
countdown_processor = CountdownProcessor(
@@ -3,8 +3,8 @@ from __future__ import annotations
from typing import Dict, Any, List
from .models.schemas import CorrectionProposal
from lyrics_transcriber.types import WordCorrection, Word
from lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.types import WordCorrection, Word
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
def adapt_proposals_to_word_corrections(
@@ -13,7 +13,7 @@ from .models.schemas import CorrectionProposal, GapClassification, GapCategory
from .workflows.correction_graph import build_correction_graph
from .prompts.classifier import build_classification_prompt
from .handlers.registry import HandlerRegistry
from lyrics_transcriber.utils.tracing import create_span, add_span_attribute
from karaoke_gen.lyrics_transcriber.utils.tracing import create_span, add_span_attribute
logger = logging.getLogger(__name__)
@@ -9,12 +9,12 @@ import json
import hashlib
# Tracing utilities (optional - gracefully handles missing dependency)
from lyrics_transcriber.utils.tracing import create_span, add_span_attribute, add_span_event
from karaoke_gen.lyrics_transcriber.utils.tracing import create_span, add_span_attribute, add_span_event
from lyrics_transcriber.types import LyricsData, PhraseScore, PhraseType, AnchorSequence, GapSequence, ScoredAnchor, TranscriptionResult, Word
from lyrics_transcriber.correction.phrase_analyzer import PhraseAnalyzer
from lyrics_transcriber.correction.text_utils import clean_text
from lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.types import LyricsData, PhraseScore, PhraseType, AnchorSequence, GapSequence, ScoredAnchor, TranscriptionResult, Word
from karaoke_gen.lyrics_transcriber.correction.phrase_analyzer import PhraseAnalyzer
from karaoke_gen.lyrics_transcriber.correction.text_utils import clean_text
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
class AnchorSequenceTimeoutError(Exception):
@@ -724,8 +724,8 @@ class AnchorSequenceFinder:
# This can happen in tests using backwards compatible constructors
# Create dummy Word objects with the text from _words if available
if hasattr(anchor, '_words') and anchor._words is not None:
from lyrics_transcriber.types import Word
from lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.types import Word
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
anchor.transcribed_words = [
Word(
id=word_id,
@@ -738,7 +738,7 @@ class AnchorSequenceFinder:
]
else:
# Create generic word objects for scoring
from lyrics_transcriber.types import Word
from karaoke_gen.lyrics_transcriber.types import Word
anchor.transcribed_words = [
Word(
id=word_id,
@@ -6,14 +6,14 @@ import os
import shortuuid
import time
from lyrics_transcriber.correction.handlers.levenshtein import LevenshteinHandler
from lyrics_transcriber.correction.handlers.no_space_punct_match import NoSpacePunctuationMatchHandler
from lyrics_transcriber.correction.handlers.relaxed_word_count_match import RelaxedWordCountMatchHandler
from lyrics_transcriber.correction.handlers.repeat import RepeatCorrectionHandler
from lyrics_transcriber.correction.handlers.sound_alike import SoundAlikeHandler
from lyrics_transcriber.correction.handlers.syllables_match import SyllablesMatchHandler
from lyrics_transcriber.correction.handlers.word_count_match import WordCountMatchHandler
from lyrics_transcriber.types import (
from karaoke_gen.lyrics_transcriber.correction.handlers.levenshtein import LevenshteinHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.no_space_punct_match import NoSpacePunctuationMatchHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.relaxed_word_count_match import RelaxedWordCountMatchHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.repeat import RepeatCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.sound_alike import SoundAlikeHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.syllables_match import SyllablesMatchHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_count_match import WordCountMatchHandler
from karaoke_gen.lyrics_transcriber.types import (
CorrectionStep,
GapSequence,
LyricsData,
@@ -23,11 +23,11 @@ from lyrics_transcriber.types import (
WordCorrection,
Word,
)
from lyrics_transcriber.correction.anchor_sequence import AnchorSequenceFinder
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.extend_anchor import ExtendAnchorHandler
from lyrics_transcriber.utils.word_utils import WordUtils
from lyrics_transcriber.utils.tracing import create_span, add_span_attribute, add_span_event
from karaoke_gen.lyrics_transcriber.correction.anchor_sequence import AnchorSequenceFinder
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.extend_anchor import ExtendAnchorHandler
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.utils.tracing import create_span, add_span_attribute, add_span_event
class LyricsCorrector:
@@ -299,9 +299,9 @@ class LyricsCorrector:
if use_agentic_env:
try:
from lyrics_transcriber.correction.agentic.agent import AgenticCorrector as _AgenticCorrector
from lyrics_transcriber.correction.agentic.adapter import adapt_proposals_to_word_corrections as _adapt
from lyrics_transcriber.correction.agentic.router import ModelRouter as _ModelRouter
from karaoke_gen.lyrics_transcriber.correction.agentic.agent import AgenticCorrector as _AgenticCorrector
from karaoke_gen.lyrics_transcriber.correction.agentic.adapter import adapt_proposals_to_word_corrections as _adapt
from karaoke_gen.lyrics_transcriber.correction.agentic.router import ModelRouter as _ModelRouter
self.logger.info("🤖 Agentic modules imported successfully - running in AGENTIC-ONLY mode")
# Create agent ONCE and reuse for all gaps (avoids repeated model initialization)
@@ -486,7 +486,7 @@ class LyricsCorrector:
# AGENTIC-ONLY MODE: Process all gaps in parallel for better performance
if use_agentic_env:
from concurrent.futures import ThreadPoolExecutor, as_completed
from lyrics_transcriber.correction.agentic.providers.config import ProviderConfig
from karaoke_gen.lyrics_transcriber.correction.agentic.providers.config import ProviderConfig
# Get parallel processing config
_config = ProviderConfig.from_env()
@@ -2,7 +2,7 @@ from abc import ABC, abstractmethod
from typing import List, Optional, Tuple, Dict, Any
import logging
from lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
class GapCorrectionHandler(ABC):
@@ -1,9 +1,9 @@
from typing import List, Optional, Tuple, Dict, Any
import logging
from lyrics_transcriber.types import GapSequence, WordCorrection, Word
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection, Word
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
class ExtendAnchorHandler(GapCorrectionHandler):
@@ -3,9 +3,9 @@ import string
import Levenshtein
import logging
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
class LevenshteinHandler(GapCorrectionHandler):
@@ -2,9 +2,9 @@ from typing import List, Optional, Tuple, Dict, Any
import logging
import re
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
class NoSpacePunctuationMatchHandler(GapCorrectionHandler):
@@ -1,9 +1,9 @@
from typing import List, Tuple, Dict, Any, Optional
import logging
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
class RelaxedWordCountMatchHandler(GapCorrectionHandler):
@@ -1,7 +1,7 @@
from typing import List, Dict, Optional, Tuple, Any
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
import logging
@@ -1,9 +1,9 @@
from typing import List, Dict, Tuple, Optional, Any
import logging
from metaphone import doublemetaphone
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
class SoundAlikeHandler(GapCorrectionHandler):
@@ -8,9 +8,9 @@ from nltk.corpus import cmudict
import syllables
from spacy_syllables import SpacySyllables
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
# Try to import preloaders (may not exist in standalone library usage)
try:
@@ -1,9 +1,9 @@
from typing import List, Tuple, Dict, Any, Optional
import logging
from lyrics_transcriber.types import GapSequence, WordCorrection
from lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from lyrics_transcriber.correction.handlers.word_operations import WordOperations
from karaoke_gen.lyrics_transcriber.types import GapSequence, WordCorrection
from karaoke_gen.lyrics_transcriber.correction.handlers.base import GapCorrectionHandler
from karaoke_gen.lyrics_transcriber.correction.handlers.word_operations import WordOperations
class WordCountMatchHandler(GapCorrectionHandler):
@@ -1,6 +1,6 @@
from typing import List, Optional, Dict, Any
from lyrics_transcriber.types import WordCorrection, GapSequence
from lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.types import WordCorrection, GapSequence
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
class WordOperations:
@@ -17,7 +17,7 @@ import logging
from typing import Dict, Any, List, Optional
from pathlib import Path
from lyrics_transcriber.types import (
from karaoke_gen.lyrics_transcriber.types import (
CorrectionResult,
WordCorrection,
LyricsSegment,
@@ -26,10 +26,10 @@ from lyrics_transcriber.types import (
TranscriptionData,
LyricsData
)
from lyrics_transcriber.correction.corrector import LyricsCorrector
from lyrics_transcriber.lyrics.user_input_provider import UserInputProvider
from lyrics_transcriber.output.generator import OutputGenerator
from lyrics_transcriber.core.config import OutputConfig
from karaoke_gen.lyrics_transcriber.correction.corrector import LyricsCorrector
from karaoke_gen.lyrics_transcriber.lyrics.user_input_provider import UserInputProvider
from karaoke_gen.lyrics_transcriber.output.generator import OutputGenerator
from karaoke_gen.lyrics_transcriber.core.config import OutputConfig
class CorrectionOperations:
@@ -2,8 +2,8 @@ from typing import List
import spacy
from spacy.tokens import Doc
import logging
from lyrics_transcriber.correction.text_utils import clean_text
from lyrics_transcriber.types import PhraseType, PhraseScore
from karaoke_gen.lyrics_transcriber.correction.text_utils import clean_text
from karaoke_gen.lyrics_transcriber.types import PhraseType, PhraseScore
# Try to import preloader (may not exist in standalone library usage)
try:
@@ -6,9 +6,9 @@ import hashlib
from pathlib import Path
import os
from abc import ABC, abstractmethod
from lyrics_transcriber.types import LyricsData, LyricsSegment, Word
from karaoke_gen.lyrics_transcriber.types import LyricsData, LyricsSegment, Word
from karaoke_lyrics_processor import KaraokeLyricsProcessor
from lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
@dataclass
@@ -2,7 +2,7 @@ from pathlib import Path
import logging
from typing import Optional, Dict, Any
from .base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from lyrics_transcriber.types import LyricsData, LyricsMetadata
from karaoke_gen.lyrics_transcriber.types import LyricsData, LyricsMetadata
from karaoke_lyrics_processor import KaraokeLyricsProcessor
@@ -3,8 +3,8 @@ import re
from typing import Optional, Dict, Any
import requests
import lyricsgenius
from lyrics_transcriber.types import LyricsData, LyricsMetadata
from lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from karaoke_gen.lyrics_transcriber.types import LyricsData, LyricsMetadata
from karaoke_gen.lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
class GeniusProvider(BaseLyricsProvider):
@@ -2,9 +2,9 @@ import logging
import re
from typing import Optional, Dict, Any, List
import requests
from lyrics_transcriber.types import LyricsData, LyricsMetadata, LyricsSegment, Word
from lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from lyrics_transcriber.utils.word_utils import WordUtils
from karaoke_gen.lyrics_transcriber.types import LyricsData, LyricsMetadata, LyricsSegment, Word
from karaoke_gen.lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from karaoke_gen.lyrics_transcriber.utils.word_utils import WordUtils
class LRCLIBProvider(BaseLyricsProvider):
@@ -1,8 +1,8 @@
import logging
from typing import Optional, Dict, Any
import requests
from lyrics_transcriber.types import LyricsData, LyricsMetadata
from lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
from karaoke_gen.lyrics_transcriber.types import LyricsData, LyricsMetadata
from karaoke_gen.lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
class MusixmatchProvider(BaseLyricsProvider):
Loaded 100 of 176 files, more files were not shown because too many files have changed in this diff. Show more