Spaces:
Running
Running
File size: 8,512 Bytes
330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 330f477 8494801 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 | from __future__ import annotations
from pathlib import Path
import numpy as np
from openmusic_analysis.analyzers import (
BGEM3LyricsAnalyzer,
BGEM3TextEncoder,
ClapAudioEncoder,
ClapGlobalAudioAnalyzer,
ClapTemporalAudioAnalyzer,
LyricsPreprocessor,
)
from openmusic_analysis.audio import AnalysisContext, AudioDecoder
from openmusic_analysis.domain import (
AnalysisResponse,
LyricsResolution,
ResolvedTrackMetadata,
TrackReference,
)
from openmusic_analysis.errors import AnalysisError
from openmusic_analysis.lyrics_resolution import LyricsLookupInput, LyricsResolver
from openmusic_analysis.registry import ModelRegistry
from openmusic_analysis.runtime import DeviceManager, InferenceGate
from openmusic_analysis.settings import Settings
DEFAULT_AUDIO_REPRESENTATIONS = ("audio.global", "audio.temporal")
class MusicAnalysisService:
def __init__(
self,
*,
registry: ModelRegistry,
decoder: AudioDecoder,
device: str,
lyrics_resolver: LyricsResolver | None = None,
) -> None:
self.registry = registry
self.decoder = decoder
self.device = device
self.lyrics_resolver = lyrics_resolver
async def analyze(
self,
source_path: str | Path,
*,
lyrics: str | None,
requested_representations: list[str] | None,
track_id: str | None,
content_identity: str | None,
lyrics_metadata: LyricsLookupInput | None = None,
) -> AnalysisResponse:
if lyrics is not None and not lyrics.strip():
raise AnalysisError(
"INVALID_LYRICS", "Lyrics must contain non-whitespace text.", status_code=422
)
should_resolve_lyrics = requested_representations is None or (
"lyrics.global" in requested_representations
)
lyrics_resolution: LyricsResolution | None = None
effective_lyrics = lyrics
if lyrics is not None or should_resolve_lyrics:
lyrics_resolution = await self.resolve_lyrics(
source_path,
provided_lyrics=lyrics,
supplied_metadata=lyrics_metadata,
)
effective_lyrics = lyrics_resolution.text
requested = self._resolve_representations(
requested_representations, effective_lyrics
)
context = AnalysisContext(source_path, self.decoder)
results = {}
for representation in requested:
analyzer = self.registry.analyzer(representation)
if analyzer.input_kind == "audio":
result = await analyzer.analyze(context)
elif analyzer.input_kind == "lyrics":
if effective_lyrics is None:
raise AnalysisError(
"LYRICS_REQUIRED",
f"Representation '{representation}' requires lyrics.",
status_code=422,
details={
"fallback_errors": [
error.model_dump()
for error in (
lyrics_resolution.errors if lyrics_resolution else []
)
]
},
)
result = await analyzer.analyze(effective_lyrics)
else:
raise RuntimeError(f"Unknown analyzer input kind: {analyzer.input_kind}")
results[representation] = result
return AnalysisResponse(
track=TrackReference(track_id=track_id, content_identity=content_identity),
representations=results,
lyrics=lyrics_resolution,
)
def _resolve_representations(
self, requested: list[str] | None, lyrics: str | None
) -> list[str]:
if requested is None:
values = list(DEFAULT_AUDIO_REPRESENTATIONS)
if lyrics is not None:
values.append("lyrics.global")
else:
values = list(dict.fromkeys(requested))
if not values:
raise AnalysisError(
"INVALID_REPRESENTATIONS",
"requested_representations must not be empty.",
status_code=422,
)
unsupported = [value for value in values if value not in self.registry.representations]
if unsupported:
raise AnalysisError(
"UNSUPPORTED_REPRESENTATION",
f"Unsupported representation(s): {', '.join(unsupported)}.",
status_code=422,
details={"supported": list(self.registry.representations)},
)
return values
async def load_models(self) -> None:
seen: set[int] = set()
for representation in self.registry.representations:
analyzer = self.registry.analyzer(representation)
encoder = getattr(analyzer, "encoder", None)
if encoder is not None and id(encoder) not in seen:
seen.add(id(encoder))
await encoder.ready()
async def rank_similar_audio(
self,
target_source_path: str | Path,
candidate_source_paths: list[str | Path],
) -> list[tuple[int, float]]:
"""Rank candidates by cosine similarity in the global CLAP space."""
analyzer = self.registry.analyzer("audio.global")
target = await analyzer.analyze(AnalysisContext(target_source_path, self.decoder))
target_embedding = np.asarray(target.embedding, dtype=np.float32)
scores: list[tuple[int, float]] = []
for index, source_path in enumerate(candidate_source_paths):
candidate = await analyzer.analyze(AnalysisContext(source_path, self.decoder))
candidate_embedding = np.asarray(candidate.embedding, dtype=np.float32)
similarity = float(np.dot(target_embedding, candidate_embedding))
scores.append((index, float(np.clip(similarity, -1.0, 1.0))))
return sorted(scores, key=lambda item: (-item[1], item[0]))
async def resolve_lyrics(
self,
source_path: str | Path,
*,
provided_lyrics: str | None = None,
supplied_metadata: LyricsLookupInput | None = None,
) -> LyricsResolution:
metadata = supplied_metadata or LyricsLookupInput()
if provided_lyrics and provided_lyrics.strip():
return LyricsResolution(
text=provided_lyrics,
source="request",
metadata=ResolvedTrackMetadata(
title=metadata.title,
artist=metadata.artist,
album=metadata.album,
isrc=metadata.isrc,
duration_seconds=metadata.duration_seconds,
),
)
if self.lyrics_resolver is None:
return LyricsResolution()
return await self.lyrics_resolver.resolve(
source_path,
provided_lyrics=provided_lyrics,
supplied_metadata=metadata,
)
def build_service(settings: Settings | None = None) -> MusicAnalysisService:
settings = settings or Settings.from_env()
device = DeviceManager.select(settings.device)
gate = InferenceGate(settings.inference_concurrency)
clap_encoder = ClapAudioEncoder(
device, gate, batch_size=settings.global_audio.inference_batch_size
)
text_encoder = BGEM3TextEncoder(device, gate)
analyzers = [
ClapGlobalAudioAnalyzer(clap_encoder, settings.global_audio),
ClapTemporalAudioAnalyzer(clap_encoder, settings.temporal_audio),
BGEM3LyricsAnalyzer(text_encoder, LyricsPreprocessor(), settings.lyrics),
]
registry = ModelRegistry(analyzers)
decoder = AudioDecoder(
ffmpeg_binary=settings.ffmpeg_binary,
ffprobe_binary=settings.ffprobe_binary,
canonical_sample_rate=settings.global_audio.sample_rate,
max_audio_seconds=settings.limits.max_audio_seconds,
timeout_seconds=settings.limits.decode_timeout_seconds,
)
lyrics_resolver = LyricsResolver(
settings.lyrics_fallback,
ffmpeg_binary=settings.ffmpeg_binary,
ffprobe_binary=settings.ffprobe_binary,
)
return MusicAnalysisService(
registry=registry,
decoder=decoder,
device=device,
lyrics_resolver=lyrics_resolver,
)
|