elif fea_pase_dev[snt].shape[0]-lab_dev[snt].shape[0]==1:
fea_lst_dev.append(fea_pase_dev[snt][:-1])
lab_lst_dev.append(lab_dev[snt])
else:
print('length error')
sys.exit(0)
else:
fea_lst_dev.append(fea_pase_dev[snt][:-2])
lab_lst_dev.append(lab_dev[snt])
# feature matrix (training)
fea_conc=np.concatenate(fea_lst)
fea_conc=context_window(fea_conc,left,right)
# feature matrix (dev)
fea_conc_dev=np.concatenate(fea_lst_dev)
fea_conc_dev=context_window(fea_conc_dev,left,right)
# feature normalization
fea_conc=(fea_conc-np.mean(fea_conc,axis=0))/np.std(fea_conc,axis=0)
fea_conc_dev=(fea_conc_dev-np.mean(fea_conc_dev,axis=0))/np.std(fea_conc_dev,axis=0)
# lab matrix
lab_conc=np.concatenate(lab_lst)
lab_conc_dev=np.concatenate(lab_lst_dev)
if right>0:
# Seeds initialization
np.random.seed(seed)
torch.manual_seed(seed)
# Batch creation (train)
fea_lst = []
lab_lst = []
print("Data Preparation...")
for snt in fea_pase.keys():
fea_lst.append(fea_pase[snt])
lab_lst.append(np.zeros(fea_pase[snt].shape[0]) + lab[snt.split('_')[0]])
# feature matrix (training)
fea_conc = np.concatenate(fea_lst)
fea_conc = context_window(fea_conc, left, right)
# feature normalization
mean = np.mean(fea_conc, axis=0)
std = np.std(fea_conc, axis=0)
# normalization
fea_conc = (fea_conc - mean) / std
mean = torch.from_numpy(mean).float().to(device)
std = torch.from_numpy(std).float().to(device)
# lab matrix
lab_conc = np.concatenate(lab_lst)
if right > 0:
fea_lst_dev.append(fea_pase_dev[snt][:-3])
lab_lst_dev.append(lab_dev[snt])
elif fea_pase_dev[snt].shape[0] - lab_dev[snt].shape[0] == 1:
fea_lst_dev.append(fea_pase_dev[snt][:-1])
lab_lst_dev.append(lab_dev[snt])
else:
print('length error')
sys.exit(0)
else:
fea_lst_dev.append(fea_pase_dev[snt][:-2])
lab_lst_dev.append(lab_dev[snt])
# feature matrix (training)
fea_conc = np.concatenate(fea_lst)
fea_conc = context_window(fea_conc, left, right)
# feature matrix (dev)
fea_conc_dev = np.concatenate(fea_lst_dev)
fea_conc_dev = context_window(fea_conc_dev, left, right)
# lab matrix
lab_conc = np.concatenate(lab_lst)
lab_conc_dev = np.concatenate(lab_lst_dev)
if right > 0:
lab_conc = lab_conc[left:-right]
lab_conc_dev = lab_conc_dev[left:-right]
else:
lab_conc = lab_conc[left:]
lab_conc_dev = lab_conc_dev[left:]
# compute per-speaker mean and variance
if avg_spk:
for spk_id in mean_spk_dev.keys():
mean_spk_dev[spk_id] = torch.mean(torch.stack(
mean_spk_dev[spk_id]),
dim=0)
std_spk_dev[spk_id] = torch.mean(torch.stack(std_spk_dev[spk_id]),
dim=0)
# apply speaker normalization
for snt_id in fea_dev.keys():
spk_id = snt_id.split('_')[0]
fea_pase_dev[snt_id] = (fea_pase_dev[snt_id] - mean_spk_dev[spk_id]
) #/std_spk_dev[spk_id]
fea_pase_dev[snt_id] = context_window(fea_pase_dev[snt_id], left,
right)
# Network initialization
inp_dim = fea_pase_dev[snt_id].shape[1] * (left + right + 1)
nnet = MLP(options, inp_dim)
nnet.to(device)
nnet.load_state_dict(torch.load(model_file))
nnet.eval()
post_file = open_or_fd(ark_file, output_folder, 'wb')
for snt_id in fea_dev.keys():
pout = nnet(torch.from_numpy(fea_pase_dev[snt_id]).to(device).float())
# TO DO IT!!
#pout=pout-log_counts
