File size: 5,858 Bytes
13e402e |
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 |
"""
Test ensemble annotation with real/synthetic audio files.
This script tests the complete annotation pipeline with actual audio,
validating both emotion and event detection.
"""
import logging
import argparse
from pathlib import Path
import sys
# Add parent directory to path
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
from ensemble_tts import EnsembleAnnotator
import numpy as np
import soundfile as sf
logging.basicConfig(level=logging.INFO, format='%(message)s')
logger = logging.getLogger(__name__)
def test_single_audio(annotator: EnsembleAnnotator, audio_path: Path):
"""Test annotation on a single audio file."""
logger.info(f"\n🎵 Testing: {audio_path.name}")
logger.info("=" * 60)
# Load audio
audio, sr = sf.read(audio_path)
logger.info(f" Audio: {len(audio)/sr:.2f}s, {sr}Hz")
# Annotate
result = annotator.annotate(audio, sample_rate=sr)
# Show results
logger.info(f"\n 📊 Emotion Results:")
logger.info(f" Label: {result['emotion']['label']}")
logger.info(f" Confidence: {result['emotion']['confidence']:.2%}")
if 'predictions' in result['emotion']:
logger.info(f"\n Individual model predictions:")
for pred in result['emotion']['predictions']:
logger.info(f" {pred['model_name']:15s}: {pred['label']:10s} ({pred.get('confidence', 0.0):.2%})")
if result.get('events') and result['events'].get('detected'):
logger.info(f"\n 🎭 Events Detected:")
for event in result['events']['detected']:
logger.info(f" - {event}")
return result
def test_dataset_sample(annotator: EnsembleAnnotator, dataset_path: Path, n_samples: int = 5):
"""Test annotation on a sample of prepared dataset."""
from datasets import load_from_disk
logger.info(f"\n📦 Loading dataset from: {dataset_path}")
dataset = load_from_disk(str(dataset_path))
logger.info(f" Total samples: {len(dataset)}")
logger.info(f" Testing {n_samples} random samples...")
# Random sample
import random
indices = random.sample(range(len(dataset)), min(n_samples, len(dataset)))
results = []
correct = 0
for i, idx in enumerate(indices, 1):
sample = dataset[idx]
audio_array = sample['audio']['array']
sr = sample['audio']['sampling_rate']
true_emotion = sample['emotion']
logger.info(f"\n{'='*60}")
logger.info(f"Sample {i}/{n_samples} - True emotion: {true_emotion}")
logger.info(f"{'='*60}")
# Annotate
result = annotator.annotate(audio_array, sample_rate=sr)
predicted_emotion = result['emotion']['label']
confidence = result['emotion']['confidence']
logger.info(f" Predicted: {predicted_emotion} ({confidence:.2%})")
if predicted_emotion == true_emotion:
logger.info(f" ✅ CORRECT")
correct += 1
else:
logger.info(f" ❌ INCORRECT (expected: {true_emotion})")
results.append({
'true': true_emotion,
'predicted': predicted_emotion,
'confidence': confidence,
'correct': predicted_emotion == true_emotion
})
# Summary
accuracy = correct / len(results)
logger.info(f"\n{'='*60}")
logger.info(f"📊 TEST SUMMARY")
logger.info(f"{'='*60}")
logger.info(f" Samples tested: {len(results)}")
logger.info(f" Correct: {correct}")
logger.info(f" Accuracy: {accuracy:.2%}")
logger.info(f"{'='*60}")
return results
def main():
parser = argparse.ArgumentParser(description="Test annotation with real audio")
parser.add_argument("--mode", type=str, default="quick",
choices=["quick", "balanced", "full"],
help="Ensemble mode")
parser.add_argument("--device", type=str, default="cpu",
choices=["cpu", "cuda"],
help="Device to use")
parser.add_argument("--audio", type=str, default=None,
help="Path to single audio file")
parser.add_argument("--dataset", type=str, default="data/prepared/synthetic_prepared",
help="Path to prepared dataset")
parser.add_argument("--samples", type=int, default=5,
help="Number of dataset samples to test")
parser.add_argument("--no-events", action="store_true",
help="Disable event detection")
args = parser.parse_args()
logger.info("\n" + "="*60)
logger.info("🎯 Ensemble Audio Annotation Test")
logger.info("="*60)
logger.info(f" Mode: {args.mode}")
logger.info(f" Device: {args.device}")
logger.info(f" Events: {'disabled' if args.no_events else 'enabled'}")
# Create annotator
logger.info("\n📦 Creating annotator...")
annotator = EnsembleAnnotator(
mode=args.mode,
device=args.device,
enable_events=not args.no_events
)
# Load models
logger.info("📥 Loading models...")
annotator.load_models()
logger.info("✅ Models loaded!")
# Test single audio file
if args.audio:
audio_path = Path(args.audio)
if not audio_path.exists():
logger.error(f"❌ Audio file not found: {audio_path}")
return 1
test_single_audio(annotator, audio_path)
# Test dataset samples
elif Path(args.dataset).exists():
test_dataset_sample(annotator, Path(args.dataset), args.samples)
else:
logger.error(f"❌ Dataset not found: {args.dataset}")
logger.error("\nCreate synthetic dataset first:")
logger.error(" python scripts/data/create_synthetic_test_data.py")
return 1
logger.info("\n✅ Test complete!")
return 0
if __name__ == "__main__":
sys.exit(main())
|