def _loadInstrumentPlugins(self):
from InstrumentLoader import InstrumentLoader
searchDirs = NSSearchPathForDirectoriesInDomains(NSApplicationSupportDirectory,
NSUserDomainMask|NSLocalDomainMask|NSNetworkDomainMask, True)
appName = u"Scotty"
searchDirs = [ os.path.join(baseDir, appName, u"Instruments") for baseDir in searchDirs ]
searchDirs.append(os.path.join(ModuleBundle.builtInPlugInsPath(), u"Instruments"))
InstrumentLoader.loadInstrumentsInSearchPaths(searchDirs)
def _loadInstrumentPlugins(self):
from InstrumentLoader import InstrumentLoader
searchDirs = [ u'~/Library/Application Support/Substance Instruments',
u'~/.substance/instruments',
u'/Library/Application Support/Substance Instruments',
u'/usr/local/share/substance/instruments',
u'/usr/share/substance/instruments',
u'/Network/Library/Application Support/Substance Instruments',
]
searchDirs = [ os.path.expanduser(searchDir) for searchDir in searchDirs ]
InstrumentLoader.loadInstrumentsInSearchPaths(searchDirs)
def _loadInstrumentPlugins(self):
from InstrumentLoader import InstrumentLoader
searchDirs = [ u'~/Library/Application Support/WILD Instruments',
u'~/.wild/instruments',
u'/Library/Application Support/WILD Instruments',
u'/usr/local/share/wild/instruments',
u'/usr/share/wild/instruments',
u'/Network/Library/Application Support/WILD Instruments',
]
searchDirs = [ os.path.expanduser(searchDir) for searchDir in searchDirs ]
for searchDir in searchDirs:
print "Searching in searchDir", searchDir
if os.path.exists(searchDir):
pluginPaths = [ os.path.join(searchDir, f) for f in os.listdir(searchDir)
if f.endswith(u'.instrument') ]
for pluginPath in pluginPaths:
try:
InstrumentLoader.loadInstrumentFromBundlePath(pluginPath)
except Exception, e:
# FIXME: Should probably alert user
pluginName = os.path.basename(pluginPath)
print u"Could not load plugin: %s: %s: %s" % (pluginName, e.__class__.__name__, e)
# |
# V
#
# ******** Fully connected layer
# |
# V
#
# ABC Per-instrument classification neurons (outputs)
#
# We vary the following parameters to find the best accuracy.
# - MFCC computation time intervals: 5ms, 10ms, 20ms, 25ms (matching various of the intervals in papers above)
# - MFCC intervals in a sliding window presented to the neural network: 3, 4, 5
# (i.e. 15ms up to 125ms when multiplied by the time intervals).
# - Training batch size
instruments = InstrumentLoader(samplesDirPath, [])
Log("Max, min MFCC rows across all instruments: ", instruments.maxMfccRows,
instruments.minMfccRows)
Log("Number of instruments by length in MFCC rows:")
for k, v in sorted(instruments.mfccLenToSamplesMap.items()):
suffix = ''
if len(v) == 1:
suffix = '(' + os.path.basename(v[0].wavPath) + ')'
Log(" ", k, ": ", len(v), suffix)
if instruments.minWavHz < wavMinAllowedHz:
print(
"ERROR: One or more wav files found with rate in Hz less than configured minimum. Min found:",
instruments.minWavHz, " allowed min:", wavMinAllowedHz)
exit(1)
import keras.models
from KerasTensorFlowAnalyzer import KerasTensorFlowAnalyzer
import MfccComparisonAnalyzer
import os
from SoundStreamAnalyzer import SoundStreamAnalyzer
import sys
if len(sys.argv) < 5:
print('Usage:')
print(' <wav-file-path> <instruments-folder-path> <model-file-path> <model-params-json-path>')
exit(1)
wavFilePath = sys.argv[1]
instrumentsFolderPath = sys.argv[2]
modelFilePath = sys.argv[3]
modelParamsPath = sys.argv[4]
trainedModel = keras.models.load_model(modelFilePath)
# See SoundModelParams.py
f = open(modelParamsPath)
modelParams = json.load(f)
orderedResultInstrumentLabels = modelParams["instruments"]
print("Ordered labels:", orderedResultInstrumentLabels)
instruments = InstrumentLoader(instrumentsFolderPath, orderedResultInstrumentLabels)
analyzers = [ KerasTensorFlowAnalyzer(trainedModel, modelParams) ] + list(MfccComparisonAnalyzer.constructFromInstruments(instruments))
analyzer = SoundStreamAnalyzer(wavFilePath, instruments, analyzers, 0.9)
analyzer.getMatches()
