import utility
from autovc.model_vc import Generator
from config import Config
from data_converter import Converter
from parallel_wavegan.utils import read_hdf5
from autovc.synthesis import build_model_melgan, melgan
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if device.type == "cuda":
print(torch.cuda.get_device_name(0))
converter = Converter(device)
import yaml
from parallel_wavegan.utils import download_pretrained_model, load_model
def logmelfilterbank(audio,
sampling_rate,
fft_size=1024,
hop_size=256,
win_length=None,
window="hann",
num_mels=80,
fmin=None,
fmax=None,
f" |-embedding.npy (single (speaker) embedding per speaker)\n"
f" |-...\n")
args = parser.parse_args()
cur_time = datetime.datetime.now().strftime("%Y%m%d_%H;%M")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
#==============================Dir settings==========================
input_dir = args.input_dir
output_dir = args.output_dir
#===========================Converter (+output dir addition)================================
if args.spectrogram_type == "standard":
log.info("Using the default AutoVC spectrogram creator")
converter = Converter(device)
elif args.spectrogram_type == "melgan":
log.info("Using a melgan spectrogram-converter for dataset generator")
converter = MelganConverter(device,
Config.dir_paths["melgan_config_path"],
Config.dir_paths["melgan_stats_path"])
#===============================create metadata (if it does not exist already)====================
if not os.path.exists(os.path.join(
output_dir,
Config.train_metadata_name)): #if metadata doesnt already exist
_ = converter.generate_train_data(input_dir, output_dir,
Config.train_metadata_name)
else:
log.warning(
f" ATTENTION: metadata already exists at: {os.path.join(output_dir, Config.train_metadata_name)}, now exiting..."
from librosa.filters import mel as librosa_mel_fn
from numpy.random import RandomState
from sklearn.preprocessing import StandardScaler
import utility
from autovc.model_vc import Generator
from config import Config
from data_converter import Converter
from parallel_wavegan.utils import read_hdf5
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if device.type == "cuda":
print(torch.cuda.get_device_name(0))
converter = Converter(device)
import yaml
from parallel_wavegan.utils import download_pretrained_model, load_model
def logmelfilterbank(
audio,
sampling_rate,
fft_size=1024, #TODO: scale this based on sampling rate as well? Otherwise each fft-frame (and spectrogram entry) is less time (e.g. at 22khz, 1024 samples is 0.05sec, while at 44khz its 0.1 sec)
hop_size=256,
win_length=None,
window="hann",
num_mels=80,
fmin=None,
source_list = ["p225_001"]
target_speaker = "Wouter"
target_list = ["1", "2", "3", "4", "5", "6", "7"]
# directories
input_dir = Config.dir_paths["input"]
converted_data_dir = Config.dir_paths["metadata"]
output_file_dir = Config.dir_paths["output"]
metadata_name = Config.metadata_name
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if device.type == "cuda":
print(torch.cuda.get_device_name(0))
converter = Converter(device)
spec_dir = Config.dir_paths["spectrograms"]
specs = converter._wav_to_spec(input_dir, spec_dir)
spect_convert_list = [('Wouter_test_wav_to_spect_to_wav', specs["Wouter"]["6"])
] #6 = "This is a test sentence"
# input_data = converter.wav_to_input(input_dir, source_speaker, target_speaker, source_list, target_list, converted_data_dir, metadata_name)
converter.output_to_wav(spect_convert_list)
print("Done")
# input_data = converter.wav_to_input(input_dir, source_speaker, target_speaker, source_list, target_list, converted_data_dir, metadata_name)
# output_data = inference(output_file_dir, device, input_data=input_data)
output_file_dir = os.path.join(output_file_dir, "griffin")
elif args.vocoder == "wavenet":
from vocoders import WaveNet
vocoder_path = os.path.join(Config.dir_paths["networks"],
Config.pretrained_names["wavenet"])
vocoder = WaveNet(device, vocoder_path)
output_file_dir = os.path.join(output_file_dir, "wavenet")
elif args.vocoder == "melgan":
from vocoders import MelGan
spectrogram_type = "melgan"
vocoder = MelGan(device)
output_file_dir = os.path.join(output_file_dir, "melgan")
sr = 16000
if spectrogram_type == "standard":
converter = Converter(device)
elif spectrogram_type == "melgan":
sr = 24000
converter = MelganConverter(device,
Config.dir_paths["melgan_config_path"],
Config.dir_paths["melgan_stats_path"])
skip = not args.force_preprocess
input_data = converter.wav_to_convert_input(input_dir,
source_speaker,
target_speaker,
source_list,
converted_data_dir,
metadata_name,
skip_existing=skip,
len_crop=args.len_crop)