if not os.path.exists(output_fldr):
os.makedirs(output_fldr)
logPath = os.path.join(output_fldr, "log.txt")
if os.path.exists(logPath): os.remove(logPath)
rep = localrepo.instance(ui.ui(), '.', False)
revision_num = rep.changelog.headrevs()[0]
# create logger
logging.basicConfig(filename=logPath, level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
logging.info("python " + " ".join(sys.argv))
logging.info("Revision number for code: " + str(revision_num))
if not arguments.normalize:
logging.info("Not normalizing inputs.")
data_src = htkdb_cm.htkdb_cm(arguments.db_name,
arguments.db_path,
arguments.num_frames_per_pt,
arguments.use_delta)
data_src._speaker_cmn = arguments.speaker_cmn
data_src._speaker_cmvn = arguments.speaker_cmvn
data_src._normalize = arguments.normalize
nn_train = nnet_train.nn()
nn_train.load(model_file)
per = perform_averaged_decoding(nn_train, data_src, arguments.num_averages,
output_fldr, arguments.db_name)
print "PER = %.4f"%per
parser.add_argument('--num_frames_per_pt',
type=int,
default=15,
help='# of frames per pt')
parser.add_argument('db_path', help='Path to validation database')
parser.add_argument('model_file',
type=str,
help='file with neural network parameters')
parser.add_argument('predictions_file', type=str, help='output folder')
arguments = parser.parse_args()
data_src = speech_data.speech_data(arguments.db_path,
arguments.num_frames_per_pt)
data_src.normalize_data()
nnet = nnet_train.nn()
nnet.load(arguments.model_file)
pred_lst, num_output_frames = nnet.create_predictions(data_src)
predictions_mat = zeros((pred_lst[-1].shape[0], num_output_frames))
utt_indices = zeros((len(pred_lst), 2), dtype='int32')
num_so_far = 0
for index, predictions in enumerate(pred_lst):
predictions_mat[:, num_so_far:(num_so_far+predictions.shape[1])] = \
predictions
utt_indices[index, 0] = num_so_far
num_so_far += predictions.shape[1]
utt_indices[index, 1] = num_so_far