Spaces:
Running
Running
File size: 1,852 Bytes
08d5f37 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
from vocoder.models.fatchord_version import WaveRNN
from vocoder import hparams as hp
import torch
_model = None # type: WaveRNN
def load_model(weights_fpath, verbose=True):
global _model, _device
if verbose:
print("Building Wave-RNN")
_model = WaveRNN(
rnn_dims=hp.voc_rnn_dims,
fc_dims=hp.voc_fc_dims,
bits=hp.bits,
pad=hp.voc_pad,
upsample_factors=hp.voc_upsample_factors,
feat_dims=hp.num_mels,
compute_dims=hp.voc_compute_dims,
res_out_dims=hp.voc_res_out_dims,
res_blocks=hp.voc_res_blocks,
hop_length=hp.hop_length,
sample_rate=hp.sample_rate,
mode=hp.voc_mode
)
if torch.cuda.is_available():
_model = _model.cuda()
_device = torch.device('cuda')
else:
_device = torch.device('cpu')
if verbose:
print("Loading model weights at %s" % weights_fpath)
checkpoint = torch.load(weights_fpath, _device)
_model.load_state_dict(checkpoint['model_state'])
_model.eval()
def is_loaded():
return _model is not None
def infer_waveform(mel, normalize=True, batched=True, target=8000, overlap=800,
progress_callback=None):
"""
Infers the waveform of a mel spectrogram output by the synthesizer (the format must match
that of the synthesizer!)
:param normalize:
:param batched:
:param target:
:param overlap:
:return:
"""
if _model is None:
raise Exception("Please load Wave-RNN in memory before using it")
if normalize:
mel = mel / hp.mel_max_abs_value
mel = torch.from_numpy(mel[None, ...])
wav = _model.generate(mel, batched, target, overlap, hp.mu_law, progress_callback)
return wav
|