OUT_PATH = args.out_path
QUANT_PATH = os.path.join(OUT_PATH, "quant/")
MEL_PATH = os.path.join(OUT_PATH, "mel/")
os.makedirs(OUT_PATH, exist_ok=True)
os.makedirs(QUANT_PATH, exist_ok=True)
os.makedirs(MEL_PATH, exist_ok=True)
wav_files = get_files(SEG_PATH)
print(" > Number of audio files : {}".format(len(wav_files)))
wav_file = wav_files[1]
m, quant, wav = process_file(wav_file)
# save an example for sanity check
if type(CONFIG.mode) is int:
wav_hat = ap.dequantize(quant)
librosa.output.write_wav(OUT_PATH + "test_converted_audio.wav",
wav_hat,
sr=CONFIG.audio['sample_rate'])
shutil.copyfile(wav_files[1], OUT_PATH + "test_target_audio.wav")
# This will take a while depending on size of dataset
with Pool(args.num_procs) as p:
dataset_ids = list(
tqdm(p.imap(extract_feats, wav_files), total=len(wav_files)))
# remove None items
if args.ignore_errors:
dataset_ids = [idx for idx in dataset_ids if idx is not None]
# save metadata
# Point SEG_PATH to a folder containing your training wavs
# Doesn't matter if it's LJspeech, CMU Arctic etc. it should work fine
SEG_PATH = CONFIG.data_path
OUT_PATH = os.path.join(CONFIG.out_path, CONFIG.run_name, "data/")
QUANT_PATH = os.path.join(OUT_PATH, "quant/")
MEL_PATH = os.path.join(OUT_PATH, "mel/")
os.makedirs(OUT_PATH, exist_ok=True)
os.makedirs(QUANT_PATH, exist_ok=True)
os.makedirs(MEL_PATH, exist_ok=True)
wav_files = get_files(SEG_PATH)
print(" > Number of audio files : {}".format(len(wav_files)))
wav_file = wav_files[1]
m, x, wav = convert_file(wav_file)
# save an example for sanity check
x = ap.dequantize(x)
librosa.output.write_wav(
OUT_PATH + "test_converted_audio.wav", x, sr=CONFIG.audio['sample_rate']
)
shutil.copyfile(wav_files[1], OUT_PATH + "test_target_audio.wav")
# This will take a while depending on size of dataset
with Pool(8) as p:
dataset_ids = list(tqdm(p.imap(process_wav, wav_files), total=len(wav_files)))
# save metadata
with open(os.path.join(OUT_PATH, "dataset_ids.pkl"), "wb") as f:
pickle.dump(dataset_ids, f)