Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2024-11-28 01:10:56 +01:00
Code Releases Wiki Activity

Merge branch 'clean' of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI into clean

Browse Source
This commit is contained in:
Ftps 2023-08-19 19:57:41 +09:00
commit c25bb6c5d5
3 changed files with 137 additions and 107 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
infer/modules/vc/modules.py
View File

@ -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()

1
infer/modules/vc/pipeline.py
View File

@ -453,4 +453,3 @@ class Pipeline(object):
if torch.cuda.is_available():
torch.cuda.empty_cache()
return audio_opt

14
infer/modules/vc/utils.py
View File

@ -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):