def testLoadBatchAudio(self, n_files, start_length, end_length):
test_audio = np.random.randn(start_length)
# Make temp dir
test_dir = tf.test.get_temp_dir()
tf.gfile.MakeDirs(test_dir)
# Make wav files
files = []
for i in range(n_files):
fname = os.path.join(test_dir, 'test_audio_{}.wav'.format(i))
files.append(fname)
librosa.output.write_wav(fname, test_audio, sr=16000, norm=True)
# Load the files
batch_data = fastgen.load_batch_audio(files, sample_length=end_length)
self.assertEqual(batch_data.shape, (n_files, end_length))
def testLoadBatchAudio(self, n_files, start_length, end_length):
test_audio = np.random.randn(start_length)
# Make temp dir
test_dir = tf.test.get_temp_dir()
tf.gfile.MakeDirs(test_dir)
# Make wav files
files = []
for i in range(n_files):
fname = os.path.join(test_dir, 'test_audio_{}.wav'.format(i))
files.append(fname)
librosa.output.write_wav(fname, test_audio, sr=16000, norm=True)
# Load the files
batch_data = fastgen.load_batch_audio(files, sample_length=end_length)
self.assertEqual(batch_data.shape, (n_files, end_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):
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)
