def analyse(self, workable):
hsh = create_hash(workable, self.identity)
cache = self.process.cache / f"{hsh}.npy"
if cache.exists():
mfcc = np.load(cache, allow_pickle=True)
else:
mfcc = get_buffer(
fluid.mfcc(
str(workable),
fftsettings=self.fftsettings,
numbands=self.numbands,
numcoeffs=self.numcoeffs,
minfreq=self.minfreq,
maxfreq=self.maxfreq,
),
"numpy",
)
np.save(cache, mfcc)
self.buffer[str(workable)] = mfcc.tolist()
def analyse(self, workable):
slices = self.input[workable]
if len(slices) == 1:
self.buffer[workable] = slices
return
count = 0
standardise = StandardScaler()
model = AgglomerativeClustering(n_clusters=self.numclusters)
while (count + self.windowsize) <= len(slices):
indices = slices[
count:count +
self.windowsize] # create a section of the indices in question
data = []
for _, (start, end) in enumerate(zip(indices, indices[1:])):
mfccs = fluid.mfcc(
workable,
fftsettings=self.fftsettings,
startframe=int(start),
numframes=int(end - start),
)
stats = get_buffer(
fluid.stats(mfccs, numderivs=self.numderivs), "numpy")
data.append(stats.flatten())
data = standardise.fit_transform(data)
cluster = model.fit(data)
cur = -2
for j, c in enumerate(cluster.labels_):
prev = cur
cur = c
if cur == prev:
try:
slices.pop(j + count)
except IndexError:
pass # FIXME why are some indices erroring?
count += 1
self.buffer[workable] = slices
print(f"At window size: {window}")
for nclusters in range(2, window):
print(f"At cluster size: {nclusters}")
model = AgglomerativeClustering(n_clusters=nclusters)
count = 0
slices = list(original_slices) # recopy the original so we start fresh
while (count + window) <= len(slices):
indices = slices[
count:count +
window] #create a section of the indices in question
data = []
for i, (start, end) in enumerate(zip(indices, indices[1:])):
mfcc = fluid.mfcc(source,
fftsettings=[2048, -1, -1],
startframe=start,
numframes=end - start)
stats = get_buffer(fluid.stats(mfcc, numderivs=1), "numpy")
data.append(stats.flatten())
data = standardise.fit_transform(data)
# might not be necessary to reduce as the dimensions are already quite low
# redux = UMAP(n_components=COMPONENTS, n_neighbors=NEIGHBOURS, min_dist=MINDIST, random_state=42).fit_transform(data)
cluster = model.fit(data)
cur = -2
for j, c in enumerate(cluster.labels_):
NEIGHBOURS = 4 # UMAP neighbours
MINDIST = 0.05 # UMAP minimum distance
PLOT = True
#HDBSCAN
HDBCLUSTSIZE = 3
HDBSAMPS = 1
media = Path("../reaper/source/media/")
source = media / "twovoice.wav"# "06-xbox controller-200518_1319.wav"# "02-200420_0928.wav"
data, labels = [], []
if not resynth.exists(): # let's not redo long NMF's each time
nmf = fluid.nmf(source, resynth=resynth, iterations=50, components=)
if not features.exists():
mfcc = fluid.mfcc(resynth, features=features, minfreq=500, maxfreq=15000, numcoeffs=13)
stats = get_buffer(fluid.stats(features, numderivs=1))
# flatten statistics because its channels...channels...channels
flatstats = []
for i in range(NMFCOMPONENTS):
offset = i * NUMCOEFFS
temp = []
for j in range(NUMCOEFFS):
for x in stats[j+offset]:
temp.append(x)
flatstats.append(temp)
# standardise data
print('Standardising Data')
standardise = StandardScaler()