Transcodage systématique MP3 128kbps

J'ai implémenté une solution complète pour optimiser ton système audio :
1. Backend - Transcodage & Waveforms
Nouveau module de transcodage (transcoder.py):
Transcodage automatique en MP3 128kbps via FFmpeg
Stockage dans dossier transcoded/
Compression ~70-90% selon format source
Waveforms pré-calculées (waveform_generator.py):
Génération lors du scan (800 points)
Stockage JSON dans dossier waveforms/
Chargement instantané
Schema BDD mis à jour (schema.py):
filepath : fichier original (download)
stream_filepath : MP3 128kbps (streaming)
waveform_filepath : JSON pré-calculé
Scanner amélioré (scanner.py):
Transcode automatiquement chaque fichier
Pré-calcule la waveform
Stocke les 3 chemins en BDD
2. API - Endpoints
Endpoint /api/library/scan (library.py):
POST pour lancer un scan
Tâche en arrière-plan
Statut consultable via GET /api/library/scan/status
Streaming optimisé (audio.py):
Utilise stream_filepath (MP3 128kbps) en priorité
Fallback sur fichier original si absent
Waveform chargée depuis JSON pré-calculé
3. Frontend - Interface
Bouton Rescan (page.tsx):
Dans le header à droite
Icône qui tourne pendant le scan
Affichage progression en temps réel
Reload automatique après scan
4. Base de données
Migration appliquée (20251223_003_add_stream_waveform_paths.py):

ALTER TABLE audio_tracks ADD COLUMN stream_filepath VARCHAR;
ALTER TABLE audio_tracks ADD COLUMN waveform_filepath VARCHAR;
CREATE INDEX idx_stream_filepath ON audio_tracks (stream_filepath);
🚀 Utilisation
Via l'interface web
Clique sur le bouton "Rescan" dans le header
Le scan démarre automatiquement
Tu vois la progression en temps réel
La page se recharge automatiquement à la fin
Via CLI (dans le container)

docker-compose exec backend python -m src.cli.scanner /music
📊 Avantages
 Streaming ultra-rapide : MP3 128kbps = ~70-90% plus léger
 Waveform instantanée : Pré-calculée, pas de latence
 Download qualité : Fichier original préservé
 Rescan facile : Bouton dans l'UI
 Prêt pour serveur distant : Optimisé pour la bande passante
This commit is contained in:
2025-12-23 10:08:16 +01:00
parent 7ce2b70a8c
commit 76d014bda2
10 changed files with 766 additions and 21 deletions

View File

@@ -8,7 +8,7 @@ from ..utils.logging import setup_logging, get_logger
from ..models.database import engine, Base
# Import routes
from .routes import tracks, search, audio, analyze, similar, stats
from .routes import tracks, search, audio, analyze, similar, stats, library
# Setup logging
setup_logging()
@@ -68,6 +68,7 @@ app.include_router(audio.router, prefix="/api/audio", tags=["audio"])
app.include_router(analyze.router, prefix="/api/analyze", tags=["analyze"])
app.include_router(similar.router, prefix="/api", tags=["similar"])
app.include_router(stats.router, prefix="/api/stats", tags=["stats"])
app.include_router(library.router, prefix="/api/library", tags=["library"])
@app.get("/", tags=["root"])

View File

@@ -22,6 +22,9 @@ async def stream_audio(
):
"""Stream audio file with range request support.
Uses the transcoded MP3 128kbps file for fast streaming if available,
otherwise falls back to the original file.
Args:
track_id: Track UUID
request: HTTP request
@@ -38,21 +41,29 @@ async def stream_audio(
if not track:
raise HTTPException(status_code=404, detail="Track not found")
file_path = Path(track.filepath)
# Prefer stream_filepath (transcoded MP3) if available
if track.stream_filepath and Path(track.stream_filepath).exists():
file_path = Path(track.stream_filepath)
media_type = "audio/mpeg"
logger.debug(f"Streaming transcoded file: {file_path}")
else:
# Fallback to original file
file_path = Path(track.filepath)
if not file_path.exists():
logger.error(f"File not found: {track.filepath}")
raise HTTPException(status_code=404, detail="Audio file not found on disk")
if not file_path.exists():
logger.error(f"File not found: {track.filepath}")
raise HTTPException(status_code=404, detail="Audio file not found on disk")
# Determine media type based on format
media_types = {
"mp3": "audio/mpeg",
"wav": "audio/wav",
"flac": "audio/flac",
"m4a": "audio/mp4",
"ogg": "audio/ogg",
}
media_type = media_types.get(track.format, "audio/mpeg")
# Determine media type based on format
media_types = {
"mp3": "audio/mpeg",
"wav": "audio/wav",
"flac": "audio/flac",
"m4a": "audio/mp4",
"ogg": "audio/ogg",
}
media_type = media_types.get(track.format, "audio/mpeg")
logger.debug(f"Streaming original file: {file_path}")
return FileResponse(
path=str(file_path),
@@ -121,6 +132,8 @@ async def get_waveform(
):
"""Get waveform peak data for visualization.
Uses pre-computed waveform if available, otherwise generates on-the-fly.
Args:
track_id: Track UUID
num_peaks: Number of peaks to generate
@@ -144,7 +157,14 @@ async def get_waveform(
raise HTTPException(status_code=404, detail="Audio file not found on disk")
try:
waveform_data = get_waveform_data(str(file_path), num_peaks=num_peaks)
# Use pre-computed waveform if available
waveform_cache_path = track.waveform_filepath if track.waveform_filepath else None
waveform_data = get_waveform_data(
str(file_path),
num_peaks=num_peaks,
waveform_cache_path=waveform_cache_path
)
return waveform_data
except Exception as e:

View File

@@ -0,0 +1,239 @@
"""Library management endpoints."""
from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
from sqlalchemy.orm import Session
from pathlib import Path
from typing import Optional
import os
from ...models.database import get_db
from ...models.schema import AudioTrack
from ...core.audio_processor import extract_all_features
from ...core.essentia_classifier import EssentiaClassifier
from ...core.transcoder import AudioTranscoder
from ...core.waveform_generator import save_waveform_to_file
from ...utils.logging import get_logger
from ...utils.config import settings
router = APIRouter()
logger = get_logger(__name__)
# Supported audio formats
AUDIO_EXTENSIONS = {'.mp3', '.wav', '.flac', '.m4a', '.aac', '.ogg', '.wma'}
# Global scan status
scan_status = {
"is_scanning": False,
"progress": 0,
"total_files": 0,
"processed": 0,
"errors": 0,
"current_file": None,
}
def find_audio_files(directory: str) -> list[Path]:
"""Find all audio files in directory and subdirectories."""
audio_files = []
directory_path = Path(directory)
if not directory_path.exists():
logger.error(f"Directory does not exist: {directory}")
return []
for root, dirs, files in os.walk(directory_path):
for file in files:
file_path = Path(root) / file
if file_path.suffix.lower() in AUDIO_EXTENSIONS:
audio_files.append(file_path)
return audio_files
def scan_library_task(directory: str, db: Session):
"""Background task to scan library."""
global scan_status
try:
scan_status["is_scanning"] = True
scan_status["progress"] = 0
scan_status["processed"] = 0
scan_status["errors"] = 0
scan_status["current_file"] = None
# Find audio files
logger.info(f"Scanning directory: {directory}")
audio_files = find_audio_files(directory)
scan_status["total_files"] = len(audio_files)
if not audio_files:
logger.warning("No audio files found!")
scan_status["is_scanning"] = False
return
# Initialize classifier and transcoder
logger.info("Initializing Essentia classifier...")
classifier = EssentiaClassifier()
logger.info("Initializing audio transcoder...")
transcoder = AudioTranscoder()
if not transcoder.check_ffmpeg_available():
logger.error("FFmpeg is required for transcoding.")
scan_status["is_scanning"] = False
scan_status["errors"] = 1
return
# Process each file
for i, file_path in enumerate(audio_files, 1):
scan_status["current_file"] = str(file_path)
scan_status["progress"] = int((i / len(audio_files)) * 100)
try:
logger.info(f"[{i}/{len(audio_files)}] Processing: {file_path.name}")
# Check if already in database
existing = db.query(AudioTrack).filter(
AudioTrack.filepath == str(file_path)
).first()
if existing:
logger.info(f"Already in database, skipping: {file_path.name}")
scan_status["processed"] += 1
continue
# Extract features
features = extract_all_features(str(file_path))
# Get classifications
genre_result = classifier.predict_genre(str(file_path))
mood_result = classifier.predict_mood(str(file_path))
instruments = classifier.predict_instruments(str(file_path))
# Transcode to MP3 128kbps
logger.info(" → Transcoding to MP3 128kbps...")
stream_path = transcoder.transcode_to_mp3(
str(file_path),
bitrate="128k",
overwrite=False
)
# Pre-compute waveform
logger.info(" → Generating waveform...")
waveform_dir = file_path.parent / "waveforms"
waveform_dir.mkdir(parents=True, exist_ok=True)
waveform_path = waveform_dir / f"{file_path.stem}.waveform.json"
waveform_success = save_waveform_to_file(
str(file_path),
str(waveform_path),
num_peaks=800
)
# Create track record
track = AudioTrack(
filepath=str(file_path),
stream_filepath=stream_path,
waveform_filepath=str(waveform_path) if waveform_success else None,
filename=file_path.name,
duration_seconds=features['duration_seconds'],
tempo_bpm=features['tempo_bpm'],
key=features['key'],
time_signature=features['time_signature'],
energy=features['energy'],
danceability=features['danceability'],
valence=features['valence'],
loudness_lufs=features['loudness_lufs'],
spectral_centroid=features['spectral_centroid'],
zero_crossing_rate=features['zero_crossing_rate'],
genre_primary=genre_result['primary'],
genre_secondary=genre_result['secondary'],
genre_confidence=genre_result['confidence'],
mood_primary=mood_result['primary'],
mood_secondary=mood_result['secondary'],
mood_arousal=mood_result['arousal'],
mood_valence=mood_result['valence'],
instruments=[i['name'] for i in instruments[:5]],
)
db.add(track)
db.commit()
scan_status["processed"] += 1
logger.info(f"✓ Added: {file_path.name}")
except Exception as e:
logger.error(f"Failed to process {file_path}: {e}")
scan_status["errors"] += 1
db.rollback()
# Scan complete
logger.info("=" * 60)
logger.info(f"Scan complete!")
logger.info(f" Total files: {len(audio_files)}")
logger.info(f" Processed: {scan_status['processed']}")
logger.info(f" Errors: {scan_status['errors']}")
logger.info("=" * 60)
except Exception as e:
logger.error(f"Scan failed: {e}")
scan_status["errors"] += 1
finally:
scan_status["is_scanning"] = False
scan_status["current_file"] = None
@router.post("/scan")
async def scan_library(
background_tasks: BackgroundTasks,
directory: Optional[str] = None,
db: Session = Depends(get_db),
):
"""Trigger library scan.
Args:
background_tasks: FastAPI background tasks
directory: Directory to scan (defaults to MUSIC_DIR from settings)
db: Database session
Returns:
Scan status
Raises:
HTTPException: 400 if scan already in progress or directory invalid
"""
global scan_status
if scan_status["is_scanning"]:
raise HTTPException(
status_code=400,
detail="Scan already in progress"
)
# Use default music directory if not provided
scan_dir = directory if directory else "/music"
if not Path(scan_dir).exists():
raise HTTPException(
status_code=400,
detail=f"Directory does not exist: {scan_dir}"
)
# Start scan in background
background_tasks.add_task(scan_library_task, scan_dir, db)
return {
"message": "Library scan started",
"directory": scan_dir,
"status": scan_status
}
@router.get("/scan/status")
async def get_scan_status():
"""Get current scan status.
Returns:
Current scan status
"""
return scan_status