def generate_cloned_samples(model,
cloning_text_path=None,
no_speakers=108,
fast=True,
p=0):
cloning_texts = ["this is the first", "this is the second"]
if (cloning_text_path == None):
cloning_text_path = "./Cloning_Audio/cloning_text.txt"
# cloning_texts = open("./Cloning_Audio/cloning_text.txt").read().splitlines()
# no_cloning_texts = len(cloning_texts)
all_speakers = []
for speaker_id in range(no_speakers):
speaker_cloning_mel = []
# print("The Speaker being cloned speaker-{}".format(speaker_id))
for text in cloning_texts:
waveform, alignment, spectrogram, mel = _tts(
model, text, p, speaker_id, fast)
speaker_cloning_mel.append(mel)
#print(np.array(speaker_cloning_mel).shape)
all_speakers.append(speaker_cloning_mel)
with open("./Cloning_Audio/speakers_cloned_voices_mel.p",
"wb") as fp: #Pickling
pickle.dump(all_speakers, fp)
# print("")
print("Shape of all speakers:", np.array(all_speakers).shape)
# print(all_speakers.shape)
# all speakers[speaker_id][cloned_audio_number]
# print(all_speakers[0][1].shape)
return all_speakers
def tts(model, text, p=0, speaker_id=0, fast=True, figures=True):
from dv3.synthesis import tts as _tts
waveform, alignment, spectrogram, mel = _tts(model, text, p, speaker_id,
fast)
if figures:
visualize(alignment, spectrogram)
IPython.display.display(Audio(waveform, rate=fs))