Spaces:
Sleeping
Sleeping
Upload 16 files
Browse files- .gitattributes +1 -0
- README.md +14 -12
- app.py +360 -0
- example2/index_link.txt +1 -0
- example2/model_link.txt +1 -0
- example2/test2.ogg +0 -0
- example3/test3.wav +0 -0
- example3/zip_link.txt +1 -0
- gitattributes +36 -0
- model.index +3 -0
- model.pth +3 -0
- models/metadata.json +152 -0
- models/model.index +3 -0
- models/model.pth +3 -0
- packages.txt +1 -0
- requirements.txt +6 -0
- test.ogg +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
model.index filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,12 +1,14 @@
|
|
1 |
-
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
-
sdk: gradio
|
7 |
-
sdk_version: 4.
|
8 |
-
app_file: app.py
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: RVC⚡ZERO
|
3 |
+
emoji: ⚡
|
4 |
+
colorFrom: gray
|
5 |
+
colorTo: indigo
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 4.28.3
|
8 |
+
app_file: app.py
|
9 |
+
license: mit
|
10 |
+
pinned: true
|
11 |
+
short_description: Voice conversion framework based on VITS
|
12 |
+
---
|
13 |
+
|
14 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import gradio as gr
|
3 |
+
import spaces
|
4 |
+
from infer_rvc_python import BaseLoader
|
5 |
+
import random
|
6 |
+
import logging
|
7 |
+
import time
|
8 |
+
import soundfile as sf
|
9 |
+
from infer_rvc_python.main import download_manager
|
10 |
+
import zipfile
|
11 |
+
import edge_tts
|
12 |
+
import asyncio
|
13 |
+
import librosa
|
14 |
+
import traceback
|
15 |
+
import soundfile as sf
|
16 |
+
from pedalboard import Pedalboard, Reverb, Compressor, HighpassFilter
|
17 |
+
from pedalboard.io import AudioFile
|
18 |
+
from pydub import AudioSegment
|
19 |
+
import noisereduce as nr
|
20 |
+
import numpy as np
|
21 |
+
import urllib.request
|
22 |
+
import shutil
|
23 |
+
import threading
|
24 |
+
|
25 |
+
logging.getLogger("infer_rvc_python").setLevel(logging.ERROR)
|
26 |
+
|
27 |
+
converter = BaseLoader(only_cpu=False, hubert_path=None, rmvpe_path=None)
|
28 |
+
|
29 |
+
title = "<center><strong><font size='7'>Vodex AI</font></strong></center>"
|
30 |
+
theme = "aliabid94/new-theme"
|
31 |
+
|
32 |
+
def find_files(directory):
|
33 |
+
file_paths = []
|
34 |
+
for filename in os.listdir(directory):
|
35 |
+
if filename.endswith('.pth') or filename.endswith('.zip') or filename.endswith('.index'):
|
36 |
+
file_paths.append(os.path.join(directory, filename))
|
37 |
+
return file_paths
|
38 |
+
|
39 |
+
def unzip_in_folder(my_zip, my_dir):
|
40 |
+
with zipfile.ZipFile(my_zip) as zip:
|
41 |
+
for zip_info in zip.infolist():
|
42 |
+
if zip_info.is_dir():
|
43 |
+
continue
|
44 |
+
zip_info.filename = os.path.basename(zip_info.filename)
|
45 |
+
zip.extract(zip_info, my_dir)
|
46 |
+
|
47 |
+
def find_my_model(a_, b_):
|
48 |
+
if a_ is None or a_.endswith(".pth"):
|
49 |
+
return a_, b_
|
50 |
+
|
51 |
+
txt_files = []
|
52 |
+
for base_file in [a_, b_]:
|
53 |
+
if base_file is not None and base_file.endswith(".txt"):
|
54 |
+
txt_files.append(base_file)
|
55 |
+
|
56 |
+
directory = os.path.dirname(a_)
|
57 |
+
|
58 |
+
for txt in txt_files:
|
59 |
+
with open(txt, 'r') as file:
|
60 |
+
first_line = file.readline()
|
61 |
+
|
62 |
+
download_manager(
|
63 |
+
url=first_line.strip(),
|
64 |
+
path=directory,
|
65 |
+
extension="",
|
66 |
+
)
|
67 |
+
|
68 |
+
for f in find_files(directory):
|
69 |
+
if f.endswith(".zip"):
|
70 |
+
unzip_in_folder(f, directory)
|
71 |
+
|
72 |
+
model = None
|
73 |
+
index = None
|
74 |
+
end_files = find_files(directory)
|
75 |
+
|
76 |
+
for ff in end_files:
|
77 |
+
if ff.endswith(".pth"):
|
78 |
+
model = os.path.join(directory, ff)
|
79 |
+
gr.Info(f"Model found: {ff}")
|
80 |
+
if ff.endswith(".index"):
|
81 |
+
index = os.path.join(directory, ff)
|
82 |
+
gr.Info(f"Index found: {ff}")
|
83 |
+
|
84 |
+
if not model:
|
85 |
+
gr.Error(f"Model not found in: {end_files}")
|
86 |
+
|
87 |
+
if not index:
|
88 |
+
gr.Warning("Index not found")
|
89 |
+
|
90 |
+
return model, index
|
91 |
+
|
92 |
+
def get_file_size(url):
|
93 |
+
if "huggingface" not in url:
|
94 |
+
raise ValueError("Only downloads from Hugging Face are allowed")
|
95 |
+
|
96 |
+
try:
|
97 |
+
with urllib.request.urlopen(url) as response:
|
98 |
+
info = response.info()
|
99 |
+
content_length = info.get("Content-Length")
|
100 |
+
|
101 |
+
file_size = int(content_length)
|
102 |
+
if file_size > 500000000:
|
103 |
+
raise ValueError("The file is too large. You can only download files up to 500 MB in size.")
|
104 |
+
|
105 |
+
except Exception as e:
|
106 |
+
raise e
|
107 |
+
|
108 |
+
def clear_files(directory):
|
109 |
+
time.sleep(15)
|
110 |
+
print(f"Clearing files: {directory}.")
|
111 |
+
shutil.rmtree(directory)
|
112 |
+
|
113 |
+
def get_my_model(url_data):
|
114 |
+
if not url_data:
|
115 |
+
return None, None
|
116 |
+
|
117 |
+
if "," in url_data:
|
118 |
+
a_, b_ = url_data.split()
|
119 |
+
a_, b_ = a_.strip().replace("/blob/", "/resolve/"), b_.strip().replace("/blob/", "/resolve/")
|
120 |
+
else:
|
121 |
+
a_, b_ = url_data.strip().replace("/blob/", "/resolve/"), None
|
122 |
+
|
123 |
+
out_dir = "downloads"
|
124 |
+
folder_download = str(random.randint(1000, 9999))
|
125 |
+
directory = os.path.join(out_dir, folder_download)
|
126 |
+
os.makedirs(directory, exist_ok=True)
|
127 |
+
|
128 |
+
try:
|
129 |
+
get_file_size(a_)
|
130 |
+
if b_:
|
131 |
+
get_file_size(b_)
|
132 |
+
|
133 |
+
valid_url = [a_] if not b_ else [a_, b_]
|
134 |
+
for link in valid_url:
|
135 |
+
download_manager(
|
136 |
+
url=link,
|
137 |
+
path=directory,
|
138 |
+
extension="",
|
139 |
+
)
|
140 |
+
|
141 |
+
for f in find_files(directory):
|
142 |
+
if f.endswith(".zip"):
|
143 |
+
unzip_in_folder(f, directory)
|
144 |
+
|
145 |
+
model = None
|
146 |
+
index = None
|
147 |
+
end_files = find_files(directory)
|
148 |
+
|
149 |
+
for ff in end_files:
|
150 |
+
if ff.endswith(".pth"):
|
151 |
+
model = ff
|
152 |
+
gr.Info(f"Model found: {ff}")
|
153 |
+
if ff.endswith(".index"):
|
154 |
+
index = ff
|
155 |
+
gr.Info(f"Index found: {ff}")
|
156 |
+
|
157 |
+
if not model:
|
158 |
+
raise ValueError(f"Model not found in: {end_files}")
|
159 |
+
|
160 |
+
if not index:
|
161 |
+
gr.Warning("Index not found")
|
162 |
+
else:
|
163 |
+
index = os.path.abspath(index)
|
164 |
+
|
165 |
+
return os.path.abspath(model), index
|
166 |
+
|
167 |
+
except Exception as e:
|
168 |
+
raise e
|
169 |
+
finally:
|
170 |
+
t = threading.Thread(target=clear_files, args=(directory,))
|
171 |
+
t.start()
|
172 |
+
|
173 |
+
def convert_now(audio_files, random_tag, converter):
|
174 |
+
return converter(
|
175 |
+
audio_files,
|
176 |
+
random_tag,
|
177 |
+
overwrite=False,
|
178 |
+
parallel_workers=8
|
179 |
+
)
|
180 |
+
|
181 |
+
def apply_noisereduce(audio_list):
|
182 |
+
print("Applying noise reduction")
|
183 |
+
|
184 |
+
result = []
|
185 |
+
for audio_path in audio_list:
|
186 |
+
out_path = f'{os.path.splitext(audio_path)[0]}_noisereduce.wav'
|
187 |
+
|
188 |
+
try:
|
189 |
+
# Load audio file
|
190 |
+
audio = AudioSegment.from_file(audio_path)
|
191 |
+
|
192 |
+
# Convert audio to numpy array
|
193 |
+
samples = np.array(audio.get_array_of_samples())
|
194 |
+
|
195 |
+
# Reduce noise
|
196 |
+
reduced_noise = nr.reduce_noise(y=samples, sr=audio.frame_rate, prop_decrease=0.6)
|
197 |
+
|
198 |
+
# Convert reduced noise signal back to audio
|
199 |
+
reduced_audio = AudioSegment(
|
200 |
+
reduced_noise.tobytes(),
|
201 |
+
frame_rate=audio.frame_rate,
|
202 |
+
sample_width=audio.sample_width,
|
203 |
+
channels=audio.channels
|
204 |
+
)
|
205 |
+
|
206 |
+
# Save reduced audio to file
|
207 |
+
reduced_audio.export(out_path, format="wav")
|
208 |
+
result.append(out_path)
|
209 |
+
|
210 |
+
except Exception as e:
|
211 |
+
traceback.print_exc()
|
212 |
+
print(f"Error in noise reduction: {str(e)}")
|
213 |
+
result.append(audio_path)
|
214 |
+
|
215 |
+
return result
|
216 |
+
|
217 |
+
def run(audio_files, file_m, file_index):
|
218 |
+
if not audio_files:
|
219 |
+
raise ValueError("Please provide an audio file.")
|
220 |
+
|
221 |
+
if isinstance(audio_files, str):
|
222 |
+
audio_files = [audio_files]
|
223 |
+
|
224 |
+
try:
|
225 |
+
duration_base = librosa.get_duration(filename=audio_files[0])
|
226 |
+
print("Duration:", duration_base)
|
227 |
+
except Exception as e:
|
228 |
+
print(e)
|
229 |
+
|
230 |
+
if file_m is not None and file_m.endswith(".txt"):
|
231 |
+
file_m, file_index = find_my_model(file_m, file_index)
|
232 |
+
print(file_m, file_index)
|
233 |
+
|
234 |
+
random_tag = "USER_" + str(random.randint(10000000, 99999999))
|
235 |
+
|
236 |
+
# Hardcoding pitch algorithm and other parameters
|
237 |
+
pitch_alg = "rmvpe+"
|
238 |
+
pitch_lvl = 0
|
239 |
+
index_inf = 0.75
|
240 |
+
r_m_f = 3
|
241 |
+
e_r = 0.25
|
242 |
+
c_b_p = 0.5
|
243 |
+
|
244 |
+
converter.apply_conf(
|
245 |
+
tag=random_tag,
|
246 |
+
file_model=file_m,
|
247 |
+
pitch_algo=pitch_alg,
|
248 |
+
pitch_lvl=pitch_lvl,
|
249 |
+
file_index=file_index,
|
250 |
+
index_influence=index_inf,
|
251 |
+
respiration_median_filtering=r_m_f,
|
252 |
+
envelope_ratio=e_r,
|
253 |
+
consonant_breath_protection=c_b_p,
|
254 |
+
resample_sr=44100 if audio_files[0].endswith('.mp3') else 0,
|
255 |
+
)
|
256 |
+
time.sleep(0.1)
|
257 |
+
|
258 |
+
result = convert_now(audio_files, random_tag, converter)
|
259 |
+
|
260 |
+
# Always apply noise reduction
|
261 |
+
result = apply_noisereduce(result)
|
262 |
+
|
263 |
+
return result
|
264 |
+
|
265 |
+
def model_conf():
|
266 |
+
model_files = [f for f in os.listdir("models") if f.endswith(".pth")]
|
267 |
+
return gr.Dropdown(
|
268 |
+
label="Select Model File",
|
269 |
+
choices=model_files,
|
270 |
+
value=model_files[0] if model_files else None,
|
271 |
+
interactive=True,
|
272 |
+
)
|
273 |
+
|
274 |
+
def index_conf():
|
275 |
+
index_files = [f for f in os.listdir("models") if f.endswith(".index")]
|
276 |
+
return gr.Dropdown(
|
277 |
+
label="Select Index File",
|
278 |
+
choices=index_files,
|
279 |
+
value=index_files[0] if index_files else None,
|
280 |
+
interactive=True,
|
281 |
+
)
|
282 |
+
|
283 |
+
def audio_conf():
|
284 |
+
return gr.File(
|
285 |
+
label="Audio files",
|
286 |
+
file_count="multiple",
|
287 |
+
type="filepath",
|
288 |
+
container=True,
|
289 |
+
)
|
290 |
+
|
291 |
+
def button_conf():
|
292 |
+
return gr.Button(
|
293 |
+
"Inference",
|
294 |
+
variant="primary",
|
295 |
+
)
|
296 |
+
|
297 |
+
def output_conf():
|
298 |
+
return gr.File(
|
299 |
+
label="Result",
|
300 |
+
file_count="multiple",
|
301 |
+
interactive=False,
|
302 |
+
)
|
303 |
+
|
304 |
+
def get_gui(theme):
|
305 |
+
with gr.Blocks(theme=theme, delete_cache=(3200, 3200)) as app:
|
306 |
+
gr.Markdown(title)
|
307 |
+
|
308 |
+
aud = audio_conf()
|
309 |
+
|
310 |
+
model = model_conf()
|
311 |
+
indx = index_conf()
|
312 |
+
button_base = button_conf()
|
313 |
+
output_base = output_conf()
|
314 |
+
|
315 |
+
button_base.click(
|
316 |
+
run,
|
317 |
+
inputs=[
|
318 |
+
aud,
|
319 |
+
model,
|
320 |
+
indx,
|
321 |
+
],
|
322 |
+
outputs=[output_base],
|
323 |
+
)
|
324 |
+
|
325 |
+
gr.Examples(
|
326 |
+
examples=[
|
327 |
+
[
|
328 |
+
["./test.ogg"],
|
329 |
+
"./model.pth",
|
330 |
+
"./model.index",
|
331 |
+
],
|
332 |
+
[
|
333 |
+
["./example2/test2.ogg"],
|
334 |
+
"./example2/model.pth",
|
335 |
+
"./example2/model.index",
|
336 |
+
],
|
337 |
+
],
|
338 |
+
fn=run,
|
339 |
+
inputs=[
|
340 |
+
aud,
|
341 |
+
model,
|
342 |
+
indx,
|
343 |
+
],
|
344 |
+
outputs=[output_base],
|
345 |
+
cache_examples=False,
|
346 |
+
)
|
347 |
+
|
348 |
+
return app
|
349 |
+
|
350 |
+
if __name__ == "__main__":
|
351 |
+
app = get_gui(theme)
|
352 |
+
app.queue(default_concurrency_limit=40)
|
353 |
+
app.launch(
|
354 |
+
max_threads=40,
|
355 |
+
share=False,
|
356 |
+
show_error=True,
|
357 |
+
quiet=False,
|
358 |
+
debug=False,
|
359 |
+
allowed_paths=["./downloads/"],
|
360 |
+
)
|
example2/index_link.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
https://huggingface.co/sail-rvc/ayaka-jp/resolve/main/model.index?download=true
|
example2/model_link.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
https://huggingface.co/sail-rvc/ayaka-jp/resolve/main/model.pth?download=true
|
example2/test2.ogg
ADDED
Binary file (118 kB). View file
|
|
example3/test3.wav
ADDED
Binary file (12.2 kB). View file
|
|
example3/zip_link.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
https://huggingface.co/Stevenojob/furina_JP/resolve/main/furina_jp.zip?download=true
|
gitattributes
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
model.index filter=lfs diff=lfs merge=lfs -text
|
model.index
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af434a9142b070f7091dcdbbf957b7a01bbc96294add99d186ef1e0d4b226eac
|
3 |
+
size 83987395
|
model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:896fcee182ecdcea6645a691366ac50153bc63015f43c981da135a8cabe2f088
|
3 |
+
size 55028048
|
models/metadata.json
ADDED
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"title": "US Ascent",
|
3 |
+
"author": {
|
4 |
+
"name": "mayank dubey",
|
5 |
+
"discordUserId": null
|
6 |
+
},
|
7 |
+
"md5": "b0a77398fc88806fda285f4ecd6a5839",
|
8 |
+
"uploadedAt": "2024-07-05T07:38:18.500Z",
|
9 |
+
"weightsLink": "https://www.weights.gg/models/cly8dvwn8000cagr4ohpzo4q2",
|
10 |
+
"id": "cly8dvwn8000cagr4ohpzo4q2",
|
11 |
+
"type": "v2",
|
12 |
+
"tags": [],
|
13 |
+
"description": "US Ascent",
|
14 |
+
"samples": [],
|
15 |
+
"files": [
|
16 |
+
{
|
17 |
+
"name": "model.index",
|
18 |
+
"size": 101587779,
|
19 |
+
"md5": "61a545d9b5bb380bed408a51708b210e"
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"name": "model.pth",
|
23 |
+
"size": 57577722,
|
24 |
+
"md5": "b0a77398fc88806fda285f4ecd6a5839"
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"torchMetadata": {
|
28 |
+
"config": {
|
29 |
+
"spec_channels": 1025,
|
30 |
+
"segment_size": 32,
|
31 |
+
"inter_channels": 192,
|
32 |
+
"hidden_channels": 192,
|
33 |
+
"filter_channels": 768,
|
34 |
+
"n_heads": 2,
|
35 |
+
"n_layers": 6,
|
36 |
+
"kernel_size": 3,
|
37 |
+
"p_dropout": 0,
|
38 |
+
"resblock": "1",
|
39 |
+
"resblock_kernel_sizes": [
|
40 |
+
3,
|
41 |
+
7,
|
42 |
+
11
|
43 |
+
],
|
44 |
+
"resblock_dilation_sizes": [
|
45 |
+
[
|
46 |
+
1,
|
47 |
+
3,
|
48 |
+
5
|
49 |
+
],
|
50 |
+
[
|
51 |
+
1,
|
52 |
+
3,
|
53 |
+
5
|
54 |
+
],
|
55 |
+
[
|
56 |
+
1,
|
57 |
+
3,
|
58 |
+
5
|
59 |
+
]
|
60 |
+
],
|
61 |
+
"upsample_rates": [
|
62 |
+
12,
|
63 |
+
10,
|
64 |
+
2,
|
65 |
+
2
|
66 |
+
],
|
67 |
+
"upsample_initial_channel": 512,
|
68 |
+
"upsample_kernel_sizes": [
|
69 |
+
24,
|
70 |
+
20,
|
71 |
+
4,
|
72 |
+
4
|
73 |
+
],
|
74 |
+
"emb_channels": null,
|
75 |
+
"spk_embed_dim": 109,
|
76 |
+
"gin_channels": 256,
|
77 |
+
"sr": 48000
|
78 |
+
},
|
79 |
+
"f0": 1,
|
80 |
+
"version": "v2",
|
81 |
+
"extra_info": {
|
82 |
+
"config": [
|
83 |
+
1025,
|
84 |
+
32,
|
85 |
+
192,
|
86 |
+
192,
|
87 |
+
768,
|
88 |
+
2,
|
89 |
+
6,
|
90 |
+
3,
|
91 |
+
0,
|
92 |
+
"1",
|
93 |
+
[
|
94 |
+
3,
|
95 |
+
7,
|
96 |
+
11
|
97 |
+
],
|
98 |
+
[
|
99 |
+
[
|
100 |
+
1,
|
101 |
+
3,
|
102 |
+
5
|
103 |
+
],
|
104 |
+
[
|
105 |
+
1,
|
106 |
+
3,
|
107 |
+
5
|
108 |
+
],
|
109 |
+
[
|
110 |
+
1,
|
111 |
+
3,
|
112 |
+
5
|
113 |
+
]
|
114 |
+
],
|
115 |
+
[
|
116 |
+
12,
|
117 |
+
10,
|
118 |
+
2,
|
119 |
+
2
|
120 |
+
],
|
121 |
+
512,
|
122 |
+
[
|
123 |
+
24,
|
124 |
+
20,
|
125 |
+
4,
|
126 |
+
4
|
127 |
+
],
|
128 |
+
109,
|
129 |
+
256,
|
130 |
+
48000
|
131 |
+
],
|
132 |
+
"epoch": 233,
|
133 |
+
"step": 6291,
|
134 |
+
"sr": 48000,
|
135 |
+
"f0": 1,
|
136 |
+
"version": "v2",
|
137 |
+
"creation_date": "2024-07-05T07:01:09.035229",
|
138 |
+
"model_hash": "7c335d1650be63dea6409d741859c137dc6827d9945d6afba08867ab4281e056"
|
139 |
+
},
|
140 |
+
"epochs": 233,
|
141 |
+
"step": 6291,
|
142 |
+
"creation_date": "2024-07-05T07:01:09.035229",
|
143 |
+
"model_hash": "7c335d1650be63dea6409d741859c137dc6827d9945d6afba08867ab4281e056"
|
144 |
+
},
|
145 |
+
"url": "https://models.weights.gg/cly79hr6d1211hlpr4obj48ab.zip",
|
146 |
+
"urls": [],
|
147 |
+
"epochs": 233,
|
148 |
+
"originalFileList": [
|
149 |
+
"model.index",
|
150 |
+
"model.pth"
|
151 |
+
]
|
152 |
+
}
|
models/model.index
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9cc11461add817f1964dfac11c37033a20037d28fe2935038d884196f556590
|
3 |
+
size 101587779
|
models/model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:595287a521b83cbd8cf8372e1a8c3200081e88ce8c0b7866ebc9db7e66be9512
|
3 |
+
size 57577722
|
packages.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
ffmpeg
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
torch==2.2.0
|
2 |
+
infer-rvc-python==1.1.0
|
3 |
+
edge-tts
|
4 |
+
pedalboard
|
5 |
+
noisereduce
|
6 |
+
numpy==1.23.5
|
test.ogg
ADDED
Binary file (73.4 kB). View file
|
|