def _store_features(self, batch, outputs, cv_spkr_name, tdir):
feats = {}
feat_type = self.conf["feat_type"]
decoded = outputs["decoded"]
for n in range(decoded.size(0)):
org_spkr_name = batch["org_spkr_name"][n]
cv_name = org_spkr_name if cv_spkr_name is None else cv_spkr_name
wavf = tdir / "{}_org-{}_cv-{}.wav".format(batch["flbl"][n],
org_spkr_name, cv_name)
wavf.parent.mkdir(parents=True, exist_ok=True)
# for feat
flen = batch["flen"][n]
feat = to_numpy(decoded[n][:flen])
feats[wavf] = {}
feats[wavf]["feats"] = self.scaler[feat_type].inverse_transform(
feat)
feats[wavf]["normed_feat"] = feat
# for f0 features
org_cf0 = self.scaler["lcf0"].inverse_transform(
to_numpy(batch["lcf0"][n][:flen]))
cv_cf0 = convert_f0(self.scaler, org_cf0, org_spkr_name, cv_name)
feats[wavf]["lcf0"] = cv_cf0
feats[wavf]["normed_lcf0"] = self.scaler["lcf0"].transform(cv_cf0)
feats[wavf]["uv"] = to_numpy(batch["uv"][n][:flen])
feats[wavf]["f0"] = np.exp(cv_cf0) * feats[wavf]["uv"]
if feat_type == "mcep":
feats[wavf]["cap"] = to_numpy(batch["cap"][n][:flen])
return feats
def _store_features(self, batch, outputs, cv_spkr_name, tdir):
feats = {}
feat_type = self.conf["feat_type"]
for n in range(outputs["decoded"].size(0)):
org_spkr_name = batch["org_spkr_name"][n]
cv_name = org_spkr_name if cv_spkr_name is None else cv_spkr_name
wavf = tdir / f"{batch['flbl'][n]}_org-{org_spkr_name}_cv-{cv_name}.wav"
# for feat
feats[wavf] = {}
flen = batch["flen"][n]
feat = to_numpy(outputs["decoded"][n][:flen])
if feat_type == "mcep" and not self.conf["use_mcep_0th"]:
mcep_0th = to_numpy(batch["mcep_0th"][n][:flen])
feat = np.hstack([mcep_0th, feat])
feats[wavf]["feats"] = self.scaler[feat_type].inverse_transform(
feat)
feats[wavf]["normed_feat"] = feat
# for f0 features
org_cf0 = self.scaler["lcf0"].inverse_transform(
to_numpy(batch["lcf0"][n][:flen]))
cv_cf0 = convert_f0(self.scaler, org_cf0, org_spkr_name, cv_name)
feats[wavf]["lcf0"] = cv_cf0
feats[wavf]["normed_lcf0"] = self.scaler["lcf0"].transform(cv_cf0)
feats[wavf]["uv"] = to_numpy(batch["uv"][n][:flen])
feats[wavf]["f0"] = np.exp(cv_cf0) * feats[wavf]["uv"]
if feat_type == "mcep":
feats[wavf]["cap"] = to_numpy(batch["cap"][n][:flen])
return feats
def reconstruction(self, batch, tdir="reconstruction"):
self.conf["n_gl_samples"] = 1
h = self._generate_conditions(batch, cv_spkr_name=None)
outputs = self.model["G"].forward(batch["feats"], dec_h=h)
self._generate_cvwav(batch, outputs, None, tdir=tdir)
if self.conf["cycle_reconstruction"]:
recondir = self.expdir / tdir / str(self.steps)
for cv_spkr_name in self.spkrs.keys():
h_cv = self._generate_conditions(batch, cv_spkr_name=cv_spkr_name)
cycle_outputs = self.model["G"].cycle_forward(
batch["feats"], org_dec_h=h, cv_dec_h=h_cv
)
recon = cycle_outputs[0]["recon"]["decoded"]
for n in range(recon.size(0)):
org_spkr_name = batch["org_spkr_name"][n]
cv_name = org_spkr_name if cv_spkr_name is None else cv_spkr_name
wavf = recondir / "{}_org-{}_cv-{}.wav".format(
batch["flbl"][n], org_spkr_name, org_spkr_name
)
flen = batch["flen"][n]
normed_feat = to_numpy(recon[n][:flen])
feat = self.scaler[self.conf["feat_type"]].inverse_transform(
normed_feat
)
mlfb2hdf5(
feat,
wavf,
ext="feats_recon_{}-{}-{}".format(
org_spkr_name, cv_name, org_spkr_name
),
)
def _get_cvf0(self, batch, spkr_name):
cv_lcf0s = []
for n in range(batch["feats"].size(0)):
org_lcf0 = self.scaler["lcf0"].inverse_transform(
to_numpy(batch["lcf0"][n]))
cv_lcf0 = convert_f0(self.scaler, org_lcf0,
batch["org_spkr_name"][n], spkr_name)
normed_cv_lcf0 = self.scaler["lcf0"].transform(cv_lcf0)
cv_lcf0s.append(torch.tensor(normed_cv_lcf0))
return torch.stack(cv_lcf0s, dim=0).float().to(self.device)
def _store_features(self, batch, outputs, cv_spkr_name, tdir):
def inv_trans(k, feat):
if k not in self.conf["ignore_scaler"]:
return self.scaler[k].inverse_transform(feat)
else:
return feat
feats = {}
feat_type = self.conf["output_feat_type"]
for n in range(outputs["decoded"].size(0)):
org_spkr_name = batch["org_spkr_name"][n]
cv_name = org_spkr_name if cv_spkr_name is None else cv_spkr_name
wavf = tdir / f"{batch['flbl'][n]}_org-{org_spkr_name}_cv-{cv_name}.wav"
# feat
feats[wavf] = {}
flen = batch["flen"][n]
feat = to_numpy(outputs["decoded"][n][:flen])
if feat_type == "mcep":
feats[wavf]["cap"] = to_numpy(batch["cap"][n][:flen])
if not self.conf["use_mcep_0th"]:
org_mcep_0th = to_numpy(batch["mcep_0th"][n][:flen])
org_mcep = to_numpy(batch["in_feats"][n][:flen])
feat = np.ascontiguousarray(np.hstack([org_mcep_0th,
feat]))
rmcep = np.ascontiguousarray(
np.hstack([org_mcep_0th, org_mcep]))
feats[wavf]["rmcep"] = inv_trans(feat_type, rmcep)
else:
feats[wavf]["rmcep"] = None
feats[wavf]["feats"] = inv_trans(feat_type, feat)
# f0
org_cf0 = inv_trans("lcf0", to_numpy(batch["lcf0"][n][:flen]))
cv_cf0 = convert_f0(self.scaler, org_cf0, org_spkr_name, cv_name)
feats[wavf]["lcf0"] = cv_cf0
feats[wavf]["uv"] = to_numpy(batch["uv"][n][:flen])
feats[wavf]["f0"] = np.exp(cv_cf0) * feats[wavf]["uv"]
# save normed one as well
feats[wavf]["normed_lcf0"] = self.scaler["lcf0"].transform(cv_cf0)
feats[wavf]["normed_feat"] = feat
return feats
