def preprocess(experiment: Experiment, args: Mapping) -> None:
""" Preprocesses wavs and text, returns None or raises an Exception. """
# bring data in format usable by Tacotron-2
# for now just copy them over
raw_wav_dir = os.path.join(experiment.paths["acoustic_model"],
"LJSpeech-1.1", "wavs")
fu.ensure_dir(raw_wav_dir)
fu.copy_files(args["wav_dir"], raw_wav_dir)
raw_metadata_file = os.path.join(experiment.paths["acoustic_model"],
"LJSpeech-1.1", "metadata.csv")
fu.copy_file(args["text_file"], raw_metadata_file)
# run Tacotron-2 preprocessing
tacoargs = namedtuple(
"tacoargs",
"base_dir hparams dataset language voice reader merge_books book output n_jobs"
.split())
tacoargs.base_dir = experiment.paths["acoustic_model"]
tacoargs.language = experiment.config["language"]
tacoargs.output = experiment.paths["acoustic_features"]
tacoargs.hparams = ""
tacoargs.n_jobs = multiprocessing.cpu_count()
# for now we always exploit the LJ settings
tacoargs.dataset = "LJSpeech-1.1"
tacoargs.voice = "female"
tacoargs.reader = "LJ"
tacoargs.merge_books = "True"
tacoargs.book = "northandsouth"
modified_hp = tacotron2.hparams.hparams.parse(tacoargs.hparams)
tacotron2.preprocess.run_preprocess(tacoargs, modified_hp)
def generate(experiment: Experiment,
sentences,
generate_features: bool = True,
generate_waveforms: bool = True) -> None:
"""
Generates from the model.
:param Experiment experiment: The experiment to generate from.
:param bool generate_features: Store acoustic features
:param bool generate_waveforms: Generate a waveform from acoustic features using Griffin-Lim
"""
# python synthesize.py --model Tacotron --tacotron_name Tacotron-2 --mode eval --text_list text_list.txt &> /dev/null
tacoargs = namedtuple(
"tacoargs",
"mode model checkpoint output_dir mels_dir hparams name tacotron_name GTA"
.split())
tacoargs.checkpoint = _get_pretrained_folder(experiment)
tacoargs.hparams = ''
tacoargs.name = "Tacotron"
tacoargs.tacotron_name = "Tacotron"
tacoargs.model = "Tacotron"
#tacoargs.input_dir = 'training_data/'
tacoargs.mels_dir = experiment.paths["acoustic2wavegen_features"]
tacoargs.output_dir = experiment.paths["acoustic2wavegen_features"]
tacoargs.mode = "eval"
tacoargs.GTA = False
#tacoargs.base_dir = ''
#tacoargs.log_dir = None
#taco_checkpoint, _, hparams = tacotron2.synthesize.prepare_run(tacoargs)
modified_hp = tacotron2.hparams.hparams.parse(tacoargs.hparams)
#taco_checkpoint = os.path.join("tacotron2", taco_checkpoint)
tacotron2.tacotron.synthesize.tacotron_synthesize(tacoargs, modified_hp,
tacoargs.checkpoint,
sentences)
output_dir = os.path.join(experiment.paths["synthesized_wavs"],
"griffinlim")
fu.ensure_dir(output_dir)
fu.copy_files(
os.path.join(experiment.paths["acoustic2wavegen_features"],
"logs-eval", "wavs"), output_dir)