def run(self, d, binary=True):
#Execute Kaldi command inputting dict d and return KaldiFormat handler
ark_in = KaldiArk('/tmp/pipe.ark', 'wb')
for key, mat in d:
ark_in.write(key, mat)
ark_in.p.close()
return self.run_file('/tmp/pipe.ark', binary)
def run(self, d, binary=True):
#Execute Kaldi command inputting dict d and return KaldiFormat handler
ark_in = KaldiArk('/tmp/pipe.ark','wb')
for key, mat in d:
ark_in.write(key, mat)
ark_in.p.close()
return self.run_file('/tmp/pipe.ark', binary)
KaldiScp('/data2/tawara/work/ttic/MyPython/src/kaldi/timit/data/fbank/train_tr90/feats.scp'), \
offsets = offset)
N_test=x_test.shape[0]
N_train=x_train.shape[0]
print "Applying batch normalization"
for i in xrange(0, N_train, batchsize):
x_batch = x_train[i : i + batchsize]
model.forward(x_batch,test=False)
logger.info("Extracting final layer")
save_to = args.save_to
print 'Saving output layer to %s' % filename+'.post.ark'
ark=KaldiArk(filename+'.post.ark','wb')
for key in frame_index:
x_batch = x_test[frame_index[key][0] : frame_index[key][1]]
ark.write(key, cuda.to_cpu(model.forward(x_batch,test=True).data))
elif args.cmd == "train":
for d in option_dict:
print d + ": " + str(option_dict[d])
ratio = float(args.ratio)
n_epoch = args.epoch
seed = args.seed
batchsize = args.batchsize
model_to = args.save_to
numpy.random.seed(seed)
context_length = args.context
offset = range(-context_length, context_length+1)
ali_to_pdf=KaldiCommand('bin/ali-to-pdf', option='/data2/tawara/work/ttic/MyPython/src/kaldi/timit/exp/tri3_ali/final.mdl')
