# Disable GPU
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
import tensorflow as tf
if __name__ == '__main__':
tf.reset_default_graph()
tf.logging.set_verbosity(tf.logging.INFO)
nnet_dir = os.path.join(args.model_dir, "nnet")
config_json = os.path.join(args.model_dir, "nnet/config.json")
if not os.path.isfile(config_json):
sys.exit("Cannot find params.json in %s" % config_json)
params = Params(config_json)
# Attention weights
params.embedding_node = "attention_weights"
with open(os.path.join(nnet_dir, "feature_dim"), "r") as f:
dim = int(f.readline().strip())
trainer = Trainer(params, args.model_dir, dim, single_cpu=True)
trainer.build("predict")
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))
import tensorflow as tf
if __name__ == '__main__':
tf.reset_default_graph()
tf.logging.set_verbosity(tf.logging.INFO)
nnet_dir = os.path.join(args.model_dir, "nnet")
config_json = os.path.join(args.model_dir, "nnet/config.json")
if not os.path.isfile(config_json):
sys.exit("Cannot find params.json in %s" % config_json)
params = Params(config_json)
# Change the output node if necessary
if len(args.node) != 0:
params.embedding_node = args.node
tf.logging.info("Extract embedding from %s" % params.embedding_node)
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")
else:
# Hack:
tf.logging.info("Use random initialization")
trainer.is_loaded = True
with tf.variable_scope("softmax", reuse=True):
kernel = tf.get_variable("output/kernel",
shape=[
trainer.embeddings.get_shape()[-1],
num_total_train_speakers
])
kernel_val = trainer.sess.run(kernel)
weights = np.transpose(kernel_val)
# Output the final activation (prior to the softmax layer)
params.embedding_node = "output"
trainer.build("predict")
if args.rspecifier.rsplit(".", 1)[1] != "scp":
# The rspecifier cannot be scp
sys.exit("The rspecifier must be scp")
spk2int = {}
with open(args.spklist, 'r') as f:
for line in f.readlines():
spk, i = line.strip().split(" ")
spk2int[spk] = int(i)
utt2spk = {}
with open(args.utt2spk, 'r') as f:
for line in f.readlines():
