Merge branch 'clean' of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI into clean
This commit is contained in:
Ftps
commit
c25bb6c5d5
@ -29,7 +29,7 @@ class VC:
|
||||
|
||||
def get_vc(self, sid, to_return_protect0, to_return_protect1):
|
||||
person = f'{os.getenv("weight_root")}/{sid}'
|
||||
print(f'loading {person}')
|
||||
print(f"loading {person}")
|
||||
|
||||
self.cpt = torch.load(person, map_location="cpu")
|
||||
self.tgt_sr = self.cpt["config"][-1]
|
||||
@ -52,10 +52,12 @@ class VC:
|
||||
("v1", 1): SynthesizerTrnMs256NSFsid,
|
||||
("v1", 0): SynthesizerTrnMs256NSFsid_nono,
|
||||
("v2", 1): SynthesizerTrnMs768NSFsid,
|
||||
("v2", 0): SynthesizerTrnMs768NSFsid_nono
|
||||
("v2", 0): SynthesizerTrnMs768NSFsid_nono,
|
||||
}
|
||||
|
||||
self.net_g = synthesizer_class.get((self.version, self.if_f0), SynthesizerTrnMs256NSFsid)(*self.cpt["config"], is_half=self.config.is_half)
|
||||
self.net_g = synthesizer_class.get(
|
||||
(self.version, self.if_f0), SynthesizerTrnMs256NSFsid
|
||||
)(*self.cpt["config"], is_half=self.config.is_half)
|
||||
|
||||
del self.net_g.enc_q
|
||||
|
||||
@ -68,20 +70,31 @@ class VC:
|
||||
|
||||
self.pipeline = Pipeline(self.tgt_sr, self.config)
|
||||
n_spk = self.cpt["config"][-3]
|
||||
index = {
|
||||
"value": get_index_path_from_model(sid),
|
||||
"__type__": "update"
|
||||
}
|
||||
index = {"value": get_index_path_from_model(sid), "__type__": "update"}
|
||||
|
||||
return (
|
||||
{"visible": True, "maximum": n_spk, "__type__": "update"},
|
||||
to_return_protect0,
|
||||
to_return_protect1,
|
||||
index,
|
||||
index
|
||||
index,
|
||||
)
|
||||
|
||||
def vc_single(self, sid, input_audio_path, f0_up_key, f0_file, f0_method, file_index, file_index2, index_rate, filter_radius, resample_sr, rms_mix_rate, protect):
|
||||
def vc_single(
|
||||
self,
|
||||
sid,
|
||||
input_audio_path,
|
||||
f0_up_key,
|
||||
f0_file,
|
||||
f0_method,
|
||||
file_index,
|
||||
file_index2,
|
||||
index_rate,
|
||||
filter_radius,
|
||||
resample_sr,
|
||||
rms_mix_rate,
|
||||
protect,
|
||||
):
|
||||
if input_audio_path is None:
|
||||
return "You need to upload an audio", None
|
||||
f0_up_key = int(f0_up_key)
|
||||
@ -135,7 +148,10 @@ class VC:
|
||||
if os.path.exists(file_index)
|
||||
else "Index not used."
|
||||
)
|
||||
return f"Success.\n {index_info}\nTime:\n npy:{times[0]}s, f0:{times[1]}s, infer:{times[2]}s", (self.tgt_sr, audio_opt)
|
||||
return (
|
||||
f"Success.\n {index_info}\nTime:\n npy:{times[0]}s, f0:{times[1]}s, infer:{times[2]}s",
|
||||
(self.tgt_sr, audio_opt),
|
||||
)
|
||||
except:
|
||||
info = traceback.format_exc()
|
||||
print(info)
|
||||
@ -156,7 +172,8 @@ class VC:
|
||||
resample_sr,
|
||||
rms_mix_rate,
|
||||
protect,
|
||||
format1):
|
||||
format1,
|
||||
):
|
||||
try:
|
||||
dir_path = (
|
||||
dir_path.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
|
||||
@ -165,7 +182,9 @@ class VC:
|
||||
os.makedirs(opt_root, exist_ok=True)
|
||||
try:
|
||||
if dir_path != "":
|
||||
paths = [os.path.join(dir_path, name) for name in os.listdir(dir_path)]
|
||||
paths = [
|
||||
os.path.join(dir_path, name) for name in os.listdir(dir_path)
|
||||
]
|
||||
else:
|
||||
paths = [path.name for path in paths]
|
||||
except:
|
||||
@ -193,7 +212,8 @@ class VC:
|
||||
tgt_sr, audio_opt = opt
|
||||
if format1 in ["wav", "flac"]:
|
||||
sf.write(
|
||||
"%s/%s.%s" % (opt_root, os.path.basename(path), format1),
|
||||
"%s/%s.%s"
|
||||
% (opt_root, os.path.basename(path), format1),
|
||||
audio_opt,
|
||||
tgt_sr,
|
||||
)
|
||||
@ -216,4 +236,3 @@ class VC:
|
||||
yield "\n".join(infos)
|
||||
except:
|
||||
yield traceback.format_exc()
|
||||
|
||||
@ -157,8 +157,8 @@ class Pipeline(object):
|
||||
replace_f0 = np.interp(
|
||||
list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1]
|
||||
)
|
||||
shape = f0[self.x_pad * tf0: self.x_pad * tf0 + len(replace_f0)].shape[0]
|
||||
f0[self.x_pad * tf0: self.x_pad * tf0 + len(replace_f0)] = replace_f0[
|
||||
shape = f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)].shape[0]
|
||||
f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)] = replace_f0[
|
||||
:shape
|
||||
]
|
||||
# with open("test_opt.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
|
||||
@ -319,14 +319,14 @@ class Pipeline(object):
|
||||
if audio_pad.shape[0] > self.t_max:
|
||||
audio_sum = np.zeros_like(audio)
|
||||
for i in range(self.window):
|
||||
audio_sum += audio_pad[i: i - self.window]
|
||||
audio_sum += audio_pad[i : i - self.window]
|
||||
for t in range(self.t_center, audio.shape[0], self.t_center):
|
||||
opt_ts.append(
|
||||
t
|
||||
- self.t_query
|
||||
+ np.where(
|
||||
np.abs(audio_sum[t - self.t_query: t + self.t_query])
|
||||
== np.abs(audio_sum[t - self.t_query: t + self.t_query]).min()
|
||||
np.abs(audio_sum[t - self.t_query : t + self.t_query])
|
||||
== np.abs(audio_sum[t - self.t_query : t + self.t_query]).min()
|
||||
)[0][0]
|
||||
)
|
||||
s = 0
|
||||
@ -374,16 +374,16 @@ class Pipeline(object):
|
||||
model,
|
||||
net_g,
|
||||
sid,
|
||||
audio_pad[s: t + self.t_pad2 + self.window],
|
||||
pitch[:, s // self.window: (t + self.t_pad2) // self.window],
|
||||
pitchf[:, s // self.window: (t + self.t_pad2) // self.window],
|
||||
audio_pad[s : t + self.t_pad2 + self.window],
|
||||
pitch[:, s // self.window : (t + self.t_pad2) // self.window],
|
||||
pitchf[:, s // self.window : (t + self.t_pad2) // self.window],
|
||||
times,
|
||||
index,
|
||||
big_npy,
|
||||
index_rate,
|
||||
version,
|
||||
protect,
|
||||
)[self.t_pad_tgt: -self.t_pad_tgt]
|
||||
)[self.t_pad_tgt : -self.t_pad_tgt]
|
||||
)
|
||||
else:
|
||||
audio_opt.append(
|
||||
@ -391,7 +391,7 @@ class Pipeline(object):
|
||||
model,
|
||||
net_g,
|
||||
sid,
|
||||
audio_pad[s: t + self.t_pad2 + self.window],
|
||||
audio_pad[s : t + self.t_pad2 + self.window],
|
||||
None,
|
||||
None,
|
||||
times,
|
||||
@ -400,7 +400,7 @@ class Pipeline(object):
|
||||
index_rate,
|
||||
version,
|
||||
protect,
|
||||
)[self.t_pad_tgt: -self.t_pad_tgt]
|
||||
)[self.t_pad_tgt : -self.t_pad_tgt]
|
||||
)
|
||||
s = t
|
||||
if if_f0 == 1:
|
||||
@ -410,15 +410,15 @@ class Pipeline(object):
|
||||
net_g,
|
||||
sid,
|
||||
audio_pad[t:],
|
||||
pitch[:, t // self.window:] if t is not None else pitch,
|
||||
pitchf[:, t // self.window:] if t is not None else pitchf,
|
||||
pitch[:, t // self.window :] if t is not None else pitch,
|
||||
pitchf[:, t // self.window :] if t is not None else pitchf,
|
||||
times,
|
||||
index,
|
||||
big_npy,
|
||||
index_rate,
|
||||
version,
|
||||
protect,
|
||||
)[self.t_pad_tgt: -self.t_pad_tgt]
|
||||
)[self.t_pad_tgt : -self.t_pad_tgt]
|
||||
)
|
||||
else:
|
||||
audio_opt.append(
|
||||
@ -435,7 +435,7 @@ class Pipeline(object):
|
||||
index_rate,
|
||||
version,
|
||||
protect,
|
||||
)[self.t_pad_tgt: -self.t_pad_tgt]
|
||||
)[self.t_pad_tgt : -self.t_pad_tgt]
|
||||
)
|
||||
audio_opt = np.concatenate(audio_opt)
|
||||
if rms_mix_rate != 1:
|
||||
@ -453,4 +453,3 @@ class Pipeline(object):
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
return audio_opt
|
||||
|
||||
@ -6,7 +6,19 @@ from fairseq import checkpoint_utils
|
||||
|
||||
|
||||
def get_index_path_from_model(sid):
|
||||
return next((f for f in [os.path.join(root, name) for root, dirs, files in os.walk(os.getenv("index_root"), topdown=False) for name in files if name.endswith(".index") and "trained" not in name] if sid.split(".")[0] in f), "")
|
||||
return next(
|
||||
(
|
||||
f
|
||||
for f in [
|
||||
os.path.join(root, name)
|
||||
for root, dirs, files in os.walk(os.getenv("index_root"), topdown=False)
|
||||
for name in files
|
||||
if name.endswith(".index") and "trained" not in name
|
||||
]
|
||||
if sid.split(".")[0] in f
|
||||
),
|
||||
"",
|
||||
)
|
||||
|
||||
|
||||
def load_hubert(config):
|
||||
|
||||
Loading…
Reference in New Issue
Block a user