def hmm_train(features):
gmmhmm = GMMHMM(n_components=30, n_mix=8)
gmmhmm.startprob_ = np.array([
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0
])
l = np.identity(30) * 0.95
for i in range(l.shape[0] - 1):
l[i, i + 1] = 0.05
l[-1, -1] = 1
gmmhmm.transmat_ = l
gmmhmm.fit(features)
preds = gmmhmm.predict(features)
print(preds)
def initialize(phones):
models = {}
start_prob = np.array([1.0, 0.0, 0.0])
transmat = np.zeros((3, 3))
for i in range(3):
for j in range(i, 3):
trans = 1 / (3 - i)
transmat[i][j] = trans
for i in phones.keys():
new_hmm = GMMHMM(n_components=3,
n_mix=5,
params='tmc',
init_params='mc')
new_hmm.startprob_ = start_prob
new_hmm.transmat_ = transmat
models[i] = new_hmm
return models
def newtrain(speakers, name):
#folder="C:/Anaconda codes/speaker reco/something new/for hack/add new people/"
folder = "C:/Anaconda codes/Hackverse/servermodel/clientfiles/"
s = list(speakers)
l = len(speakers)
#name= input("enter your name")
speakers.append(name)
new_person = speakers[l]
#rint(new_person)
try:
os.makedirs("clientfiles/dataset/" + name)
except:
print("already exists")
return (s)
#os.mkdir(folder+"dataset/"+ name)
x = "clientfiles/dataset/" + name + "/"
samples(x)
training_speaker_name = name
file_path = x
file_names = os.listdir(file_path)
#print((len(file_names)))
lengths = np.empty(len(file_names))
#print(np.shape(lengths))
feature_vectors = np.empty([20, 0])
for i in range(len(file_names)):
x, rate = librosa.load(file_path + file_names[i]) #loads the file
#rate, x = wavfile.read(file_names[i])
x = librosa.feature.mfcc(y=x[0:int(len(x) / 1.25)],
sr=rate) #extracts mfcc
#x = mfcc(x[0:len(x)/1.25], samplerate=rate)
lengths[i] = int(len(x.transpose()))
#print(np.shape(x))
feature_vectors = np.concatenate((feature_vectors, x), axis=1)
#feature_vectors = np.vstack((feature_vectors, x.transpose()))
#print(((lengths)))
#print(np.shape(feature_vectors))
#TRAINING A MODEL
N = 3 # Number of States of HMM
Mixtures = 64 # Number of Gaussian Mixtures.
model = GMMHMM(n_components=N, n_mix=Mixtures, covariance_type='diag')
startprob = np.ones(N) * (10**(-30)) # Left to Right Model
startprob[0] = 1.0 - (N - 1) * (10**(-30))
transmat = np.zeros([N, N]) # Initial Transmat for Left to Right Model
#print(startprob,'\n',transmat)
for i in range(N):
for j in range(N):
transmat[i, j] = 1 / (N - i)
transmat = np.triu(transmat, k=0)
transmat[transmat == 0] = (10**(-30))
model = GMMHMM(n_components=N,
n_mix=Mixtures,
covariance_type='diag',
init_params="mcw",
n_iter=100)
model.startprob_ = startprob
model.transmat_ = transmat
#print(startprob,'\n',transmat)
feature = feature_vectors.transpose()
#print(np.shape(feature))
lengths = [int(x) for x in lengths]
#print(type(lengths[0]))
model.fit(feature, lengths)
joblib.dump(model, folder + "/models/" + name + ".pkl")
return (speakers)
startprob[0] = 1.0 - (N - 1) * (10**(-30))
transmat = np.zeros([N, N]) # Initial Transmat for Left to Right Model
print(startprob, '\n', transmat)
for i in range(N):
for j in range(N):
transmat[i, j] = 1 / (N - i)
transmat = np.triu(transmat, k=0)
transmat[transmat == 0] = (10**(-30))
model = GMMHMM(n_components=N,
n_mix=Mixtures,
covariance_type='diag',
init_params="mcw",
n_iter=100)
model.startprob_ = startprob
model.transmat_ = transmat
print(startprob, '\n', transmat)
feature = feature_vectors.transpose()
print(np.shape(feature))
lengths = [int(x) for x in lengths]
print(type(lengths[0]))
model.fit(feature, lengths)
joblib.dump(
model, "C:/Anaconda codes/speaker reco/something new/for hack/models/" +
training_speaker_name + ".pkl")
n_mix=1,
random_state=42,
n_iter=1000,
verbose=True,
params='mctw',
init_params='mc',
# startprob_prior = np.array([1.0,0.0,0.0,0.0,0.0]),
# transmat_prior = np.array([
# [0.7,0.3,0.0,0.0,0.0],
# [0.0,0.7,0.3,0.0,0.0],
# [0.0,0.0,0.7,0.3,0.0],
# [0.0,0.0,0.0,0.7,0.3],
# [0.0,0.0,0.0,0.0,1.0],
# ])
)
hmm.startprob_ = np.array([1.0, 0.0, 0.0, 0.0, 0.0])
# hmm.transmat_ = np.array([
# [0.7,0.3,0.0,0.0,0.0],
# [0.0,0.7,0.3,0.0,0.0],
# [0.0,0.0,0.7,0.3,0.0],
# [0.0,0.0,0.0,0.7,0.3],
# [0.0,0.0,0.0,0.0,1.0],
# ])
# uncomment below line to train with full dataset
# X = np.concatenate(dataset[cname])
# lengths = list([len(x) for x in dataset[cname]])
# hmm.fit(X, lengths=lengths)
X = np.concatenate(dataset_train[cname])
lengths = list([len(x) for x in dataset_train[cname]])
