Spaces:
Sleeping
Sleeping
File size: 3,140 Bytes
33f35c7 | 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 | from __future__ import annotations
import json
import tempfile
import uuid
from pathlib import Path
import gradio as gr
import soundfile as sf
try:
import spaces
except ImportError:
class spaces:
class GPU:
def __init__(self, func=None, duration=60):
self.func = func
def __call__(self, *args, **kwargs):
if self.func is not None:
return self.func(*args, **kwargs)
return args[0]
from pyharp import ModelCard, build_endpoint
from music2emo_runtime import analyze_music
MIN_AUDIO_SECONDS = 1
MAX_AUDIO_SECONDS = 60
OUTPUT_ROOT = Path(tempfile.gettempdir()) / "music2emo_outputs"
model_card = ModelCard(
name="Music2Emo",
description=(
"Recognize music emotion as mood tags and continuous "
"valence-arousal scores."
),
author="AMAAI Lab",
tags=[
"music-information-retrieval",
"music-emotion-recognition",
"mood-tagging",
"valence",
"arousal",
],
)
def _validate_audio(path: str | None) -> str:
if not path:
raise gr.Error("Please upload an audio file.")
try:
duration = sf.info(path).duration
except Exception as exc:
raise gr.Error(f"Could not read the audio file: {exc}") from exc
if duration < MIN_AUDIO_SECONDS:
raise gr.Error("Audio must be at least 1 second long.")
if duration > MAX_AUDIO_SECONDS:
raise gr.Error(
f"Audio must be no longer than {MAX_AUDIO_SECONDS} seconds. "
f"Received {duration:.1f} seconds."
)
return path
@spaces.GPU(duration=120)
def process_fn(audio_path: str | None, threshold: float) -> str:
audio_path = _validate_audio(audio_path)
try:
result = analyze_music(audio_path, threshold)
except Exception as exc:
raise gr.Error(f"Music2Emo inference failed: {exc}") from exc
output_dir = OUTPUT_ROOT / uuid.uuid4().hex
output_dir.mkdir(parents=True, exist_ok=True)
output_path = output_dir / "music2emo_analysis.json"
output_path.write_text(json.dumps(result, indent=2) + "\n", encoding="utf-8")
return str(output_path)
with gr.Blocks(title="Music2Emo") as demo:
input_components = [
gr.Audio(type="filepath", label="Music Audio")
.harp_required(True)
.set_info("Music clip between 1 and 60 seconds."),
gr.Slider(
minimum=0.1,
maximum=0.9,
value=0.5,
step=0.05,
label="Mood Threshold",
).set_info("Minimum probability for a mood tag to be returned."),
]
output_components = [
gr.File(
type="filepath",
file_types=[".json"],
label="Emotion Analysis",
).set_info("Mood probabilities and valence-arousal scores."),
]
build_endpoint(
model_card=model_card,
input_components=input_components,
output_components=output_components,
process_fn=process_fn,
)
if __name__ == "__main__":
demo.queue(default_concurrency_limit=1).launch(show_error=True, pwa=True)
|