def main(unused_argv=None):
os.environ["CUDA_VISIBLE_DEVICES"] = str(FLAGS.gpu_number)
source_path = utils.shell_path(FLAGS.source_path)
checkpoint_path = utils.shell_path(FLAGS.checkpoint_path)
save_path = utils.shell_path(FLAGS.save_path)
if not save_path:
raise RuntimeError("Must specify a save_path.")
tf.logging.set_verbosity(FLAGS.log)
# Generate from wav files
if tf.gfile.IsDirectory(source_path):
files = tf.gfile.ListDirectory(source_path)
exts = [os.path.splitext(f)[1] for f in files]
if ".wav" in exts:
postfix = ".wav"
elif ".npy" in exts:
postfix = ".npy"
else:
raise RuntimeError("Folder must contain .wav or .npy files.")
postfix = ".npy" if FLAGS.npy_only else postfix
files = sorted([
os.path.join(source_path, fname) for fname in files
if fname.lower().endswith(postfix)
])
elif source_path.lower().endswith((".wav", ".npy")):
files = [source_path]
else:
files = []
# Now synthesize from files one batch at a time
batch_size = FLAGS.batch_size
sample_length = FLAGS.sample_length
n = len(files)
for start in range(0, n, batch_size):
end = start + batch_size
batch_files = files[start:end]
save_names = [
os.path.join(
save_path,
"gen_" + os.path.splitext(os.path.basename(f))[0] + ".wav")
for f in batch_files
]
print('loading batch..')
batch_data = fastgen.load_batch(batch_files,
sample_length=sample_length)
# Encode waveforms
encodings = batch_data if postfix == ".npy" else fastgen.encode(
batch_data, checkpoint_path, sample_length=sample_length)
if FLAGS.gpu_number != 0:
with tf.device("/device:GPU:%d" % FLAGS.gpu_number):
fastgen.synthesize(encodings,
save_names,
checkpoint_path=checkpoint_path)
else:
fastgen.synthesize(encodings,
save_names,
checkpoint_path=checkpoint_path)
def main(unused_argv=None):
os.environ["CUDA_VISIBLE_DEVICES"] = str(FLAGS.gpu_number)
source_path = utils.shell_path(FLAGS.source_path)
checkpoint_path = utils.shell_path(FLAGS.checkpoint_path)
save_path = utils.shell_path(FLAGS.save_path)
if not save_path:
raise RuntimeError("Must specify a save_path.")
tf.logging.set_verbosity(FLAGS.log)
# Generate from wav files
if tf.gfile.IsDirectory(source_path):
files = tf.gfile.ListDirectory(source_path)
exts = [os.path.splitext(f)[1] for f in files]
if ".wav" in exts:
postfix = ".wav"
elif ".npy" in exts:
postfix = ".npy"
else:
raise RuntimeError("Folder must contain .wav or .npy files.")
postfix = ".npy" if FLAGS.npy_only else postfix
files = sorted([
os.path.join(source_path, fname)
for fname in files
if fname.lower().endswith(postfix)
])
elif source_path.lower().endswith((".wav", ".npy")):
files = [source_path]
else:
files = []
# Now synthesize from files one batch at a time
batch_size = FLAGS.batch_size
sample_length = FLAGS.sample_length
n = len(files)
for start in range(0, n, batch_size):
end = start + batch_size
batch_files = files[start:end]
save_names = [
os.path.join(save_path,
"gen_" + os.path.splitext(os.path.basename(f))[0] + ".wav")
for f in batch_files
]
batch_data = fastgen.load_batch(batch_files, sample_length=sample_length)
# Encode waveforms
encodings = batch_data if postfix == ".npy" else fastgen.encode(
batch_data, checkpoint_path, sample_length=sample_length)
if FLAGS.gpu_number != 0:
with tf.device("/device:GPU:%d" % FLAGS.gpu_number):
fastgen.synthesize(
encodings, save_names, checkpoint_path=checkpoint_path)
else:
fastgen.synthesize(encodings, save_names, checkpoint_path=checkpoint_path)
def main(unused_argv=None):
source_path = utils.shell_path(FLAGS.source_path)
checkpoint_path = utils.shell_path(FLAGS.checkpoint_path)
save_path = utils.shell_path(FLAGS.save_path)
if not save_path:
raise RuntimeError("Must specify a save_path.")
tf.logging.set_verbosity(FLAGS.log)
# Generate from wav files
if tf.gfile.IsDirectory(source_path):
files = tf.gfile.ListDirectory(source_path)
exts = [os.path.splitext(f)[1] for f in files]
if ".wav" in exts:
postfix = ".wav"
elif ".npy" in exts:
postfix = ".npy"
else:
raise RuntimeError("Folder must contain .wav or .npy files.")
postfix = ".npy" if FLAGS.encodings else postfix
files = sorted([
os.path.join(source_path, fname) for fname in files
if fname.lower().endswith(postfix)
])
elif source_path.lower().endswith(postfix):
files = [source_path]
else:
files = []
for f in files:
out_file = os.path.join(
save_path,
"gen_" + os.path.splitext(os.path.basename(f))[0] + ".wav")
tf.logging.info("OUTFILE %s" % out_file)
synthesize(source_file=f,
checkpoint_path=checkpoint_path,
out_file=out_file,
sample_length=FLAGS.sample_length)
def main(unused_argv=None):
os.environ["CUDA_VISIBLE_DEVICES"] = str(FLAGS.gpu_number)
source_path = utils.shell_path(FLAGS.source_path)
checkpoint_path = utils.shell_path(FLAGS.checkpoint_path)
save_path = utils.shell_path(FLAGS.save_path)
if not save_path:
raise ValueError("Must specify a save_path.")
tf.logging.set_verbosity(FLAGS.log)
# Use directory of files
if tf.gfile.IsDirectory(source_path):
files = tf.gfile.ListDirectory(source_path)
file_extensions = [os.path.splitext(f)[1] for f in files]
if ".wav" in file_extensions:
file_extension = ".wav"
elif ".npy" in file_extensions:
file_extension = ".npy"
else:
raise RuntimeError("Folder must contain .wav or .npy files.")
file_extension = ".npy" if FLAGS.npy_only else file_extension
files = sorted([
os.path.join(source_path, fname) for fname in files
if fname.lower().endswith(file_extension)
])
# Use a single file
elif source_path.lower().endswith((".wav", ".npy")):
file_extension = os.path.splitext(source_path.lower())[1]
files = [source_path]
else:
raise ValueError(
"source_path {} must be a folder or file.".format(source_path))
# Now synthesize from files one batch at a time
batch_size = FLAGS.batch_size
sample_length = FLAGS.sample_length
n = len(files)
for start in range(0, n, batch_size):
end = start + batch_size
batch_files = files[start:end]
save_names = [
os.path.join(
save_path,
"gen_" + os.path.splitext(os.path.basename(f))[0] + ".wav")
for f in batch_files
]
# Encode waveforms
if file_extension == ".wav":
batch_data = fastgen.load_batch_audio(batch_files,
sample_length=sample_length)
encodings = fastgen.encode(batch_data,
checkpoint_path,
sample_length=sample_length)
# Or load encodings
else:
encodings = fastgen.load_batch_encodings(
batch_files, sample_length=sample_length)
# Synthesize multi-gpu
if FLAGS.gpu_number != 0:
with tf.device("/device:GPU:%d" % FLAGS.gpu_number):
fastgen.synthesize(encodings,
save_names,
checkpoint_path=checkpoint_path)
# Single gpu
else:
fastgen.synthesize(encodings,
save_names,
checkpoint_path=checkpoint_path)
def main(unused_argv=None):
tf.logging.set_verbosity(FLAGS.log)
if FLAGS.checkpoint_path:
checkpoint_path = utils.shell_path(FLAGS.checkpoint_path)
else:
expdir = utils.shell_path(FLAGS.expdir)
tf.logging.info("Will load latest checkpoint from %s.", expdir)
while not tf.gfile.Exists(expdir):
tf.logging.fatal("\tExperiment save dir '%s' does not exist!", expdir)
sys.exit(1)
try:
checkpoint_path = tf.train.latest_checkpoint(expdir)
except tf.errors.NotFoundError:
tf.logging.fatal("There was a problem determining the latest checkpoint.")
sys.exit(1)
if not tf.train.checkpoint_exists(checkpoint_path):
tf.logging.fatal("Invalid checkpoint path: %s", checkpoint_path)
sys.exit(1)
tf.logging.info("Will restore from checkpoint: %s", checkpoint_path)
source_path = utils.shell_path(FLAGS.source_path)
tf.logging.info("Will load Wavs from %s." % source_path)
save_path = utils.shell_path(FLAGS.save_path)
tf.logging.info("Will save embeddings to %s." % save_path)
if not tf.gfile.Exists(save_path):
tf.logging.info("Creating save directory...")
tf.gfile.MakeDirs(save_path)
sample_length = FLAGS.sample_length
batch_size = FLAGS.batch_size
def is_wav(f):
return f.lower().endswith(".wav")
wavfiles = sorted([
os.path.join(source_path, fname)
for fname in tf.gfile.ListDirectory(source_path) if is_wav(fname)
])
for start_file in xrange(0, len(wavfiles), batch_size):
batch_number = (start_file / batch_size) + 1
tf.logging.info("On file number %s (batch %d).", start_file, batch_number)
end_file = start_file + batch_size
wavefiles_batch = wavfiles[start_file:end_file]
# Ensure that files has batch_size elements.
batch_filler = batch_size - len(wavefiles_batch)
wavefiles_batch.extend(batch_filler * [wavefiles_batch[-1]])
wav_data = np.array(
[utils.load_audio(f, sample_length) for f in wavefiles_batch])
try:
tf.reset_default_graph()
# Load up the model for encoding and find the encoding
encoding = encode(wav_data, checkpoint_path, sample_length=sample_length)
if encoding.ndim == 2:
encoding = np.expand_dims(encoding, 0)
tf.logging.info("Encoding:")
tf.logging.info(encoding.shape)
tf.logging.info("Sample length: %d" % sample_length)
for num, (wavfile, enc) in enumerate(zip(wavefiles_batch, encoding)):
filename = "%s_embeddings.npy" % wavfile.split("/")[-1].strip(".wav")
with tf.gfile.Open(os.path.join(save_path, filename), "w") as f:
np.save(f, enc)
if num + batch_filler + 1 == batch_size:
break
except Exception as e:
tf.logging.info("Unexpected error happened: %s.", e)
raise
def main(unused_argv=None):
os.environ["CUDA_VISIBLE_DEVICES"] = str(FLAGS.gpu_number)
source_path = utils.shell_path(FLAGS.source_path)
checkpoint_path = utils.shell_path(FLAGS.checkpoint_path)
save_path = utils.shell_path(FLAGS.save_path)
if not save_path:
raise ValueError("Must specify a save_path.")
tf.logging.set_verbosity(FLAGS.log)
# Use directory of files
if tf.gfile.IsDirectory(source_path):
files = tf.gfile.ListDirectory(source_path)
file_extensions = [os.path.splitext(f)[1] for f in files]
if ".wav" in file_extensions:
file_extension = ".wav"
elif ".npy" in file_extensions:
file_extension = ".npy"
else:
raise RuntimeError("Folder must contain .wav or .npy files.")
file_extension = ".npy" if FLAGS.npy_only else file_extension
files = sorted([
os.path.join(source_path, fname)
for fname in files
if fname.lower().endswith(file_extension)
])
# Use a single file
elif source_path.lower().endswith((".wav", ".npy")):
file_extension = os.path.splitext(source_path.lower())[1]
files = [source_path]
else:
raise ValueError(
"source_path {} must be a folder or file.".format(source_path))
# Now synthesize from files one batch at a time
batch_size = FLAGS.batch_size
sample_length = FLAGS.sample_length
n = len(files)
for start in range(0, n, batch_size):
end = start + batch_size
batch_files = files[start:end]
save_names = [
os.path.join(save_path,
"gen_" + os.path.splitext(os.path.basename(f))[0] + ".wav")
for f in batch_files
]
# Encode waveforms
if file_extension == ".wav":
batch_data = fastgen.load_batch_audio(
batch_files, sample_length=sample_length)
encodings = fastgen.encode(
batch_data, checkpoint_path, sample_length=sample_length)
# Or load encodings
else:
encodings = fastgen.load_batch_encodings(
batch_files, sample_length=sample_length)
# Synthesize multi-gpu
if FLAGS.gpu_number != 0:
with tf.device("/device:GPU:%d" % FLAGS.gpu_number):
fastgen.synthesize(
encodings, save_names, checkpoint_path=checkpoint_path)
# Single gpu
else:
fastgen.synthesize(
encodings, save_names, checkpoint_path=checkpoint_path)
