bacow/GPT-SoVITS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Introduce Docker and Windows CI Workflow, Pre-commit Formatting, and Language Resource Auto-Download (#2351)

Browse Source 
* Docker Auto-Build Workflow

* Rename

* Update

* Fix Bugs

* Disable Progress Bar When workflows triggered

* Fix Wget

* Fix Bugs

* Fix Bugs

* Update Wget

* Update Workflows

* Accelerate Docker Image Building

* Fix Install.sh

* Add Skip-Check For Action Runner

* Fix Dockerfile

* .

* .

* .

* .

* Delete File in Runner

* Add Sort

* Delete More Files

* Delete More

* .

* .

* .

* Add Pre-Commit Hook
Update Docker

* Add Code Spell Check

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* Fix Bugs

* .

* Disable Progress Bar and Logs while using GitHub Actions

* .

* .

* Fix Bugs

* update conda

* fix bugs

* Fix Bugs

* fix bugs

* .

* .

* Quiet Installation

* fix bugs

* .

* fix bug

* .

* Fix pre-commit.ci and Docker

* fix bugs

* .

* Update Docker & Pre-Commit

* fix  bugs

* Update Req

* Update Req

* Update OpenCC

* update precommit

* .

* Update .pre-commit-config.yaml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update Docs and fix bugs

* Fix \

* Fix MacOS

* .

* test

* .

* Add Tag Alias

* .

* fix bugs

* fix bugs

* make image smaller

* update pre-commit config

* .

* .

* fix bugs

* use miniconda

* Fix Wrong Path

* .

* debug

* debug

* revert

* Fix Bugs

* Update Docs, Add Dict Auto Download in install.sh

* update docker_build

* Update Docs for Install.sh

* update docker docs about architecture

* Add Xcode-Commandline-Tool Installation

* Update Docs

1. Add Missing VC17
2. Modufied the Order of FFmpeg Installation and Requirements Installation
3. Remove Duplicate FFmpeg

* Fix Wrong Cuda Version

* Update TESTED ENV

* Add PYTHONNOUSERSITE(-s)

* Fix Wrapper

* Update install.sh For Robustness

* Ignore .git

* Preload CUDNN For Ctranslate2

* Remove Gradio Warnings

* Update Colab

* Fix OpenCC Problems

* Update Win DLL Strategy

* Fix Onnxruntime-gpu NVRTC Error

* Fix Path Problems

* Add Windows Packages Workflow

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* .

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* Fix Path

* Fix Path

* Enable Logging

* Set 7-Zip compression level to maximum (-mx=9)

* Use Multithread in ONNX Session

* Fix Tag Bugs

* Add Time

* Add Time

* Add Time

* Compress More

* Copy DLL to Solve VC Runtime DLL Missing Issues

* Expose FFmpeg Errors, Copy Only Part of Visual C++ Runtime

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* WIP

* WIP

* WIP

* Update build_windows_packages.ps1

* Update install.sh

* Update build_windows_packages.ps1

* Update docker-publish.yaml

* Update install.sh

* Update Dockerfile

* Update docker_build.sh

* Update miniconda_install.sh

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update Colab-WebUI.ipynb

* Update Colab-Inference.ipynb

* Update docker-compose.yaml

* 更新 build_windows_packages.ps1

* Update install.sh

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
XXXXRT666
2025-05-26 05:45:14 +03:00
committed by GitHub
parent 13055fa569
commit d5e479dad6
58 changed files with 2096 additions and 987 deletions
Download Patch File Download Diff File Expand all files Collapse all files

119
tools/uvr5/lib/lib_v5/spec_utils.py
View File

@@ -27,9 +27,7 @@ def crop_center(h1, h2):
return h1
def wave_to_spectrogram(
wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
):
def wave_to_spectrogram(wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False):
if reverse:
wave_left = np.flip(np.asfortranarray(wave[0]))
wave_right = np.flip(np.asfortranarray(wave[1]))
@@ -43,7 +41,7 @@ def wave_to_spectrogram(
wave_left = np.asfortranarray(wave[0])
wave_right = np.asfortranarray(wave[1])
spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
spec = np.asfortranarray([spec_left, spec_right])
@@ -51,9 +49,7 @@ def wave_to_spectrogram(
return spec
def wave_to_spectrogram_mt(
wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
):
def wave_to_spectrogram_mt(wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False):
import threading
if reverse:
@@ -103,21 +99,13 @@ def combine_spectrograms(specs, mp):
raise ValueError("Too much bins")
# lowpass fiter
if (
mp.param["pre_filter_start"] > 0
): # and mp.param['band'][bands_n]['res_type'] in ['scipy', 'polyphase']:
if mp.param["pre_filter_start"] > 0: # and mp.param['band'][bands_n]['res_type'] in ['scipy', 'polyphase']:
if bands_n == 1:
spec_c = fft_lp_filter(
spec_c, mp.param["pre_filter_start"], mp.param["pre_filter_stop"]
)
spec_c = fft_lp_filter(spec_c, mp.param["pre_filter_start"], mp.param["pre_filter_stop"])
else:
gp = 1
for b in range(
mp.param["pre_filter_start"] + 1, mp.param["pre_filter_stop"]
):
g = math.pow(
10, -(b - mp.param["pre_filter_start"]) * (3.5 - gp) / 20.0
)
for b in range(mp.param["pre_filter_start"] + 1, mp.param["pre_filter_stop"]):
g = math.pow(10, -(b - mp.param["pre_filter_start"]) * (3.5 - gp) / 20.0)
gp = g
spec_c[:, b, :] *= g
@@ -189,9 +177,7 @@ def mask_silence(mag, ref, thres=0.2, min_range=64, fade_size=32):
else:
e += fade_size
mag[:, :, s + fade_size : e - fade_size] += ref[
:, :, s + fade_size : e - fade_size
]
mag[:, :, s + fade_size : e - fade_size] += ref[:, :, s + fade_size : e - fade_size]
old_e = e
return mag
@@ -207,9 +193,7 @@ def cache_or_load(mix_path, inst_path, mp):
mix_basename = os.path.splitext(os.path.basename(mix_path))[0]
inst_basename = os.path.splitext(os.path.basename(inst_path))[0]
cache_dir = "mph{}".format(
hashlib.sha1(json.dumps(mp.param, sort_keys=True).encode("utf-8")).hexdigest()
)
cache_dir = "mph{}".format(hashlib.sha1(json.dumps(mp.param, sort_keys=True).encode("utf-8")).hexdigest())
mix_cache_dir = os.path.join("cache", cache_dir)
inst_cache_dir = os.path.join("cache", cache_dir)
@@ -230,31 +214,27 @@ def cache_or_load(mix_path, inst_path, mp):
if d == len(mp.param["band"]): # high-end band
X_wave[d], _ = librosa.load(
mix_path,
sr = bp["sr"],
mono = False,
dtype = np.float32,
res_type = bp["res_type"]
mix_path, sr=bp["sr"], mono=False, dtype=np.float32, res_type=bp["res_type"]
)
y_wave[d], _ = librosa.load(
inst_path,
sr = bp["sr"],
mono = False,
dtype = np.float32,
res_type = bp["res_type"],
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
else: # lower bands
X_wave[d] = librosa.resample(
X_wave[d + 1],
orig_sr = mp.param["band"][d + 1]["sr"],
target_sr = bp["sr"],
res_type = bp["res_type"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
y_wave[d] = librosa.resample(
y_wave[d + 1],
orig_sr = mp.param["band"][d + 1]["sr"],
target_sr = bp["sr"],
res_type = bp["res_type"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
X_wave[d], y_wave[d] = align_wave_head_and_tail(X_wave[d], y_wave[d])
@@ -302,9 +282,7 @@ def spectrogram_to_wave(spec, hop_length, mid_side, mid_side_b2, reverse):
if reverse:
return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
elif mid_side:
return np.asfortranarray(
[np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
)
return np.asfortranarray([np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)])
elif mid_side_b2:
return np.asfortranarray(
[
@@ -326,9 +304,7 @@ def spectrogram_to_wave_mt(spec, hop_length, mid_side, reverse, mid_side_b2):
global wave_left
wave_left = librosa.istft(**kwargs)
thread = threading.Thread(
target=run_thread, kwargs={"stft_matrix": spec_left, "hop_length": hop_length}
)
thread = threading.Thread(target=run_thread, kwargs={"stft_matrix": spec_left, "hop_length": hop_length})
thread.start()
wave_right = librosa.istft(spec_right, hop_length=hop_length)
thread.join()
@@ -336,9 +312,7 @@ def spectrogram_to_wave_mt(spec, hop_length, mid_side, reverse, mid_side_b2):
if reverse:
return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
elif mid_side:
return np.asfortranarray(
[np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
)
return np.asfortranarray([np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)])
elif mid_side_b2:
return np.asfortranarray(
[
@@ -357,21 +331,15 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
for d in range(1, bands_n + 1):
bp = mp.param["band"][d]
spec_s = np.ndarray(
shape=(2, bp["n_fft"] // 2 + 1, spec_m.shape[2]), dtype=complex
)
spec_s = np.ndarray(shape=(2, bp["n_fft"] // 2 + 1, spec_m.shape[2]), dtype=complex)
h = bp["crop_stop"] - bp["crop_start"]
spec_s[:, bp["crop_start"] : bp["crop_stop"], :] = spec_m[
:, offset : offset + h, :
]
spec_s[:, bp["crop_start"] : bp["crop_stop"], :] = spec_m[:, offset : offset + h, :]
offset += h
if d == bands_n: # higher
if extra_bins_h: # if --high_end_process bypass
max_bin = bp["n_fft"] // 2
spec_s[:, max_bin - extra_bins_h : max_bin, :] = extra_bins[
:, :extra_bins_h, :
]
spec_s[:, max_bin - extra_bins_h : max_bin, :] = extra_bins[:, :extra_bins_h, :]
if bp["hpf_start"] > 0:
spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
if bands_n == 1:
@@ -405,9 +373,9 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
mp.param["mid_side_b2"],
mp.param["reverse"],
),
orig_sr = bp["sr"],
target_sr = sr,
res_type = "sinc_fastest",
orig_sr=bp["sr"],
target_sr=sr,
res_type="sinc_fastest",
)
else: # mid
spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
@@ -456,10 +424,7 @@ def mirroring(a, spec_m, input_high_end, mp):
np.abs(
spec_m[
:,
mp.param["pre_filter_start"]
- 10
- input_high_end.shape[1] : mp.param["pre_filter_start"]
- 10,
mp.param["pre_filter_start"] - 10 - input_high_end.shape[1] : mp.param["pre_filter_start"] - 10,
:,
]
),
@@ -467,19 +432,14 @@ def mirroring(a, spec_m, input_high_end, mp):
)
mirror = mirror * np.exp(1.0j * np.angle(input_high_end))
return np.where(
np.abs(input_high_end) <= np.abs(mirror), input_high_end, mirror
)
return np.where(np.abs(input_high_end) <= np.abs(mirror), input_high_end, mirror)
if "mirroring2" == a:
mirror = np.flip(
np.abs(
spec_m[
:,
mp.param["pre_filter_start"]
- 10
- input_high_end.shape[1] : mp.param["pre_filter_start"]
- 10,
mp.param["pre_filter_start"] - 10 - input_high_end.shape[1] : mp.param["pre_filter_start"] - 10,
:,
]
),
@@ -528,7 +488,6 @@ def istft(spec, hl):
if __name__ == "__main__":
import argparse
import sys
import time
import cv2
@@ -573,10 +532,10 @@ if __name__ == "__main__":
if d == len(mp.param["band"]): # high-end band
wave[d], _ = librosa.load(
args.input[i],
sr = bp["sr"],
mono = False,
dtype = np.float32,
res_type = bp["res_type"],
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
if len(wave[d].shape) == 1: # mono to stereo
@@ -584,9 +543,9 @@ if __name__ == "__main__":
else: # lower bands
wave[d] = librosa.resample(
wave[d + 1],
orig_sr = mp.param["band"][d + 1]["sr"],
target_sr = bp["sr"],
res_type = bp["res_type"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
spec[d] = wave_to_spectrogram(