trainer = Trainer(params, args.model_dir, single_cpu=True)
with open(os.path.join(nnet_dir, "feature_dim"), "r") as f:
dim = int(f.readline().strip())
#trainer.build("predict", dim=dim)
trainer.build("predict",
dim=dim,
loss_type="extract_asoftmax",
num_speakers=154)
if args.rspecifier.rsplit(".", 1)[1] == "scp":
# The rspecifier cannot be scp
sys.exit("The rspecifier must be ark or input pipe")
fp_out = open_or_fd(args.wspecifier, "wb")
for index, (key, feature) in enumerate(read_mat_ark(args.rspecifier)):
if feature.shape[0] < args.min_chunk_size:
tf.logging.info("[INFO] Key %s length too short, %d < %d, skip." %
(key, feature.shape[0], args.min_chunk_size))
continue
if feature.shape[0] > args.chunk_size:
feature_array = []
feature_length = []
num_chunks = int(
np.ceil(
float(feature.shape[0] - args.chunk_size) /
(args.chunk_size / 2))) + 1
tf.logging.info(
"[INFO] Key %s length %d > %d, split to %d segments." %
(key, feature.shape[0], args.chunk_size, num_chunks))
for i in range(num_chunks):
trainer = Trainer(params, args.model_dir, single_cpu=True)
with open(os.path.join(nnet_dir, "feature_dim"), "r") as f:
dim = int(f.readline().strip())
trainer.build("predict", dim=dim)
vad_dir = args.rspecifier.split(":")[5].split()[0]
#tf.logging.info(vad_dir)
write_dir = args.wspecifier.split(":")[3].split(",")
#tf.logging.info(args.wspecifier)
while True:
if os.path.isfile(vad_dir):
#start = time.time()
fp_out = open_or_fd(args.wspecifier, "wb")
for index, (key,
feature) in enumerate(read_mat_ark(args.rspecifier)):
if feature.shape[0] < args.min_chunk_size:
tf.logging.info(
"[INFO] Key %s length too short, %d < %d, skip." %
(key, feature.shape[0], args.min_chunk_size))
continue
if feature.shape[0] > args.chunk_size:
feature_array = []
feature_length = []
num_chunks = int(
np.ceil(
float(feature.shape[0] - args.chunk_size) /
(args.chunk_size / 2))) + 1
tf.logging.info(
"[INFO] Key %s length %d > %d, split to %d segments." %
(key, feature.shape[0], args.chunk_size, num_chunks))