StarMirror/MockingBird
1
0
Fork 0
mirror of https://github.com/babysor/MockingBird.git synced 2024-03-22 13:11:31 +08:00
Code Issues Projects Releases Wiki Activity

修复兼容性 - mac + linux

Browse Source
This commit is contained in:
babysor00 2022-06-25 20:17:06 +08:00
parent ee643d7cbc
commit 885225045d
4 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
mkgui/app.py
View File

@ -15,12 +15,12 @@ from typing import Any, Tuple
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
# Constants # Constants
AUDIO_SAMPLES_DIR = 'samples\\' AUDIO_SAMPLES_DIR = f"samples{os.sep}"
SYN_MODELS_DIRT = "synthesizer\\saved_models" SYN_MODELS_DIRT = f"synthesizer{os.sep}saved_models"
ENC_MODELS_DIRT = "encoder\\saved_models" ENC_MODELS_DIRT = f"encoder{os.sep}saved_models"
VOC_MODELS_DIRT = "vocoder\\saved_models" VOC_MODELS_DIRT = f"vocoder{os.sep}saved_models"
TEMP_SOURCE_AUDIO = "wavs\\temp_source.wav" TEMP_SOURCE_AUDIO = f"wavs{os.sep}temp_source.wav"
TEMP_RESULT_AUDIO = "wavs\\temp_result.wav" TEMP_RESULT_AUDIO = f"wavs{os.sep}temp_result.wav"
# Load local sample audio as options TODO: load dataset # Load local sample audio as options TODO: load dataset
if os.path.isdir(AUDIO_SAMPLES_DIR): if os.path.isdir(AUDIO_SAMPLES_DIR):

20
mkgui/app_vc.py
View File

@ -14,18 +14,18 @@ import re
import numpy as np import numpy as np
from mkgui.base.components.types import FileContent from mkgui.base.components.types import FileContent
from vocoder.hifigan import inference as gan_vocoder from vocoder.hifigan import inference as gan_vocoder
from typing import Any from typing import Any, Tuple
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
# Constants # Constants
AUDIO_SAMPLES_DIR = 'samples\\' AUDIO_SAMPLES_DIR = f'sample{os.sep}'
EXT_MODELS_DIRT = "ppg_extractor\\saved_models" EXT_MODELS_DIRT = f'ppg_extractor{os.sep}saved_models'
CONV_MODELS_DIRT = "ppg2mel\\saved_models" CONV_MODELS_DIRT = f'ppg2mel{os.sep}saved_models'
VOC_MODELS_DIRT = "vocoder\\saved_models" VOC_MODELS_DIRT = f'vocoder{os.sep}saved_models'
TEMP_SOURCE_AUDIO = "wavs/temp_source.wav" TEMP_SOURCE_AUDIO = f'wavs{os.sep}temp_source.wav'
TEMP_TARGET_AUDIO = "wavs/temp_target.wav" TEMP_TARGET_AUDIO = f'wavs{os.sep}temp_target.wav'
TEMP_RESULT_AUDIO = "wavs/temp_result.wav" TEMP_RESULT_AUDIO = f'wavs{os.sep}temp_result.wav'
# Load local sample audio as options TODO: load dataset # Load local sample audio as options TODO: load dataset
if os.path.isdir(AUDIO_SAMPLES_DIR): if os.path.isdir(AUDIO_SAMPLES_DIR):
@ -80,7 +80,7 @@ class AudioEntity(BaseModel):
mel: Any mel: Any
class Output(BaseModel): class Output(BaseModel):
__root__: tuple[AudioEntity, AudioEntity, AudioEntity] __root__: Tuple[AudioEntity, AudioEntity, AudioEntity]
def render_output_ui(self, streamlit_app, input) -> None: # type: ignore def render_output_ui(self, streamlit_app, input) -> None: # type: ignore
"""Custom output UI. """Custom output UI.
@ -135,7 +135,7 @@ def convert(input: Input) -> Output:
# Import necessary dependency of Voice Conversion # Import necessary dependency of Voice Conversion
from utils.f0_utils import compute_f0, f02lf0, compute_mean_std, get_converted_lf0uv from utils.f0_utils import compute_f0, f02lf0, compute_mean_std, get_converted_lf0uv
ref_lf0_mean, ref_lf0_std = compute_mean_std(f02lf0(compute_f0(ref_wav))) ref_lf0_mean, ref_lf0_std = compute_mean_std(f02lf0(compute_f0(ref_wav)))
speacker_encoder.load_model(Path("encoder/saved_models/pretrained_bak_5805000.pt")) speacker_encoder.load_model(Path("encoder{os.sep}saved_models{os.sep}pretrained_bak_5805000.pt"))
embed = speacker_encoder.embed_utterance(ref_wav) embed = speacker_encoder.embed_utterance(ref_wav)
lf0_uv = get_converted_lf0uv(src_wav, ref_lf0_mean, ref_lf0_std, convert=True) lf0_uv = get_converted_lf0uv(src_wav, ref_lf0_mean, ref_lf0_std, convert=True)
min_len = min(ppg.shape[1], len(lf0_uv)) min_len = min(ppg.shape[1], len(lf0_uv))

8
mkgui/preprocess.py
View File

@ -2,12 +2,12 @@ from pydantic import BaseModel, Field
import os import os
from pathlib import Path from pathlib import Path
from enum import Enum from enum import Enum
from typing import Any from typing import Any, Tuple
# Constants # Constants
EXT_MODELS_DIRT = "ppg_extractor\\saved_models" EXT_MODELS_DIRT = f"ppg_extractor{os.sep}saved_models"
ENC_MODELS_DIRT = "encoder\\saved_models" ENC_MODELS_DIRT = f"encoder{os.sep}saved_models"
if os.path.isdir(EXT_MODELS_DIRT): if os.path.isdir(EXT_MODELS_DIRT):
@ -70,7 +70,7 @@ class AudioEntity(BaseModel):
mel: Any mel: Any
class Output(BaseModel): class Output(BaseModel):
__root__: tuple[str, int] __root__: Tuple[str, int]
def render_output_ui(self, streamlit_app, input) -> None: # type: ignore def render_output_ui(self, streamlit_app, input) -> None: # type: ignore
"""Custom output UI. """Custom output UI.

10
mkgui/train.py
View File

@ -2,7 +2,7 @@ from pydantic import BaseModel, Field
import os import os
from pathlib import Path from pathlib import Path
from enum import Enum from enum import Enum
from typing import Any from typing import Any, Tuple
import numpy as np import numpy as np
from utils.load_yaml import HpsYaml from utils.load_yaml import HpsYaml
from utils.util import AttrDict from utils.util import AttrDict
@ -10,9 +10,9 @@ import torch
# TODO: seperator for *unix systems # TODO: seperator for *unix systems
# Constants # Constants
EXT_MODELS_DIRT = "ppg_extractor\\saved_models" EXT_MODELS_DIRT = f"ppg_extractor{os.sep}saved_models"
CONV_MODELS_DIRT = "ppg2mel\\saved_models" CONV_MODELS_DIRT = f"ppg2mel{os.sep}saved_models"
ENC_MODELS_DIRT = "encoder\\saved_models" ENC_MODELS_DIRT = f"encoder{os.sep}saved_models"
if os.path.isdir(EXT_MODELS_DIRT): if os.path.isdir(EXT_MODELS_DIRT):
@ -102,7 +102,7 @@ class AudioEntity(BaseModel):
mel: Any mel: Any
class Output(BaseModel): class Output(BaseModel):
__root__: tuple[str, int] __root__: Tuple[str, int]
def render_output_ui(self, streamlit_app, input) -> None: # type: ignore def render_output_ui(self, streamlit_app, input) -> None: # type: ignore
"""Custom output UI. """Custom output UI.