from rvc import *
#region RVC WebUI App
from argparse import ArgumentParser
import sys
if len(sys.argv) > 1:
warning = sys.argv[1].lower() == 'true'
else:
warning = False # Default value if no argument is provided
if warning == 'True':
print("\n-------------------------------\nRVC v2 Easy GUI (Local Edition)\n-------------------------------\n")
else:
print("\n-------------------------------\nRVC v2 Easy GUI (Colab Edition)\n-------------------------------\n")
def get_presets():
data = None
with open('../inference-presets.json', 'r') as file:
data = json.load(file)
preset_names = []
for preset in data['presets']:
preset_names.append(preset['name'])
return preset_names
def change_choices2():
audio_files=[]
for filename in os.listdir("./audios"):
if filename.endswith(('.wav','.mp3','.ogg','.flac','.m4a','.aac','.mp4')):
audio_files.append(os.path.join('./audios',filename).replace('\\', '/'))
return {"choices": sorted(audio_files), "__type__": "update"}, {"__type__": "update"}
audio_files=[]
for filename in os.listdir("./audios"):
if filename.endswith(('.wav','.mp3','.ogg','.flac','.m4a','.aac','.mp4')):
audio_files.append(os.path.join('./audios',filename).replace('\\', '/'))
def get_index():
if check_for_name() != '':
chosen_model=sorted(names)[0].split(".")[0]
logs_path="./logs/"+chosen_model
if os.path.exists(logs_path):
for file in os.listdir(logs_path):
if file.endswith(".index"):
return os.path.join(logs_path, file)
return ''
else:
return ''
def get_indexes():
indexes_list=[]
for dirpath, dirnames, filenames in os.walk("./logs/"):
for filename in filenames:
if filename.endswith(".index"):
indexes_list.append(os.path.join(dirpath,filename))
if len(indexes_list) > 0:
return indexes_list
else:
return ''
def get_name():
if len(audio_files) > 0:
return sorted(audio_files)[0]
else:
return ''
def save_to_wav(record_button):
if record_button is None:
pass
else:
path_to_file=record_button
new_name = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")+'.wav'
new_path='./audios/'+new_name
shutil.move(path_to_file,new_path)
return new_path
def save_to_wav2(dropbox):
file_path=dropbox.name
shutil.move(file_path,'./audios')
return os.path.join('./audios',os.path.basename(file_path))
def match_index(sid0):
folder=sid0.split(".")[0]
parent_dir="./logs/"+folder
if os.path.exists(parent_dir):
for filename in os.listdir(parent_dir):
if filename.endswith(".index"):
index_path=os.path.join(parent_dir,filename)
return index_path
else:
return ''
def check_for_name():
if len(names) > 0:
return sorted(names)[0]
else:
return ''
def download_from_url(url, model):
if url == '':
return "URL cannot be left empty."
if model =='':
return "You need to name your model. For example: My-Model"
url = url.strip()
zip_dirs = ["zips", "unzips"]
for directory in zip_dirs:
if os.path.exists(directory):
shutil.rmtree(directory)
os.makedirs("zips", exist_ok=True)
os.makedirs("unzips", exist_ok=True)
zipfile = model + '.zip'
zipfile_path = './zips/' + zipfile
try:
if "drive.google.com" in url:
subprocess.run(["gdown", url, "--fuzzy", "-O", zipfile_path])
elif "mega.nz" in url:
m = Mega()
m.download_url(url, './zips')
else:
subprocess.run(["wget", url, "-O", zipfile_path])
for filename in os.listdir("./zips"):
if filename.endswith(".zip"):
zipfile_path = os.path.join("./zips/",filename)
shutil.unpack_archive(zipfile_path, "./unzips", 'zip')
else:
return "No zipfile found."
for root, dirs, files in os.walk('./unzips'):
for file in files:
file_path = os.path.join(root, file)
if file.endswith(".index"):
os.mkdir(f'./logs/{model}')
shutil.copy2(file_path,f'./logs/{model}')
elif "G_" not in file and "D_" not in file and file.endswith(".pth"):
shutil.copy(file_path,f'./weights/{model}.pth')
shutil.rmtree("zips")
shutil.rmtree("unzips")
return "Success."
except:
return "There's been an error."
def success_message(face):
return f'{face.name} has been uploaded.', 'None'
eleven_voices = ['Adam','Antoni','Josh','Arnold','Sam','Bella','Rachel','Domi','Elli']
eleven_voices_ids=['pNInz6obpgDQGcFmaJgB','ErXwobaYiN019PkySvjV','TxGEqnHWrfWFTfGW9XjX','VR6AewLTigWG4xSOukaG','yoZ06aMxZJJ28mfd3POQ','EXAVITQu4vr4xnSDxMaL','21m00Tcm4TlvDq8ikWAM','AZnzlk1XvdvUeBnXmlld','MF3mGyEYCl7XYWbV9V6O']
chosen_voice = dict(zip(eleven_voices, eleven_voices_ids))
def stoptraining(mim):
if int(mim) == 1:
try:
CSVutil('csvdb/stop.csv', 'w+', 'stop', 'True')
os.kill(PID, signal.SIGTERM)
except Exception as e:
print(f"Couldn't click due to {e}")
return (
{"visible": False, "__type__": "update"},
{"visible": True, "__type__": "update"},
)
def elevenTTS(xiapi, text, id, lang):
if xiapi!= '' and id !='':
choice = chosen_voice[id]
CHUNK_SIZE = 1024
url = f"https://api.elevenlabs.io/v1/text-to-speech/{choice}"
headers = {
"Accept": "audio/mpeg",
"Content-Type": "application/json",
"xi-api-key": xiapi
}
if lang == 'en':
data = {
"text": text,
"model_id": "eleven_monolingual_v1",
"voice_settings": {
"stability": 0.5,
"similarity_boost": 0.5
}
}
else:
data = {
"text": text,
"model_id": "eleven_multilingual_v1",
"voice_settings": {
"stability": 0.5,
"similarity_boost": 0.5
}
}
response = requests.post(url, json=data, headers=headers)
with open('./temp_eleven.mp3', 'wb') as f:
for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
if chunk:
f.write(chunk)
aud_path = save_to_wav('./temp_eleven.mp3')
return aud_path, aud_path
else:
tts = gTTS(text, lang=lang)
tts.save('./temp_gTTS.mp3')
aud_path = save_to_wav('./temp_gTTS.mp3')
return aud_path, aud_path
def upload_to_dataset(files, dir):
if dir == '':
dir = './dataset'
if not os.path.exists(dir):
os.makedirs(dir)
count = 0
for file in files:
path=file.name
shutil.copy2(path,dir)
count += 1
return f' {count} files uploaded to {dir}.'
def zip_downloader(model):
if not os.path.exists(f'./weights/{model}.pth'):
return {"__type__": "update"}, f'Make sure the Voice Name is correct. I could not find {model}.pth'
index_found = False
for file in os.listdir(f'./logs/{model}'):
if file.endswith('.index') and 'added' in file:
log_file = file
index_found = True
if index_found:
return [f'./weights/{model}.pth', f'./logs/{model}/{log_file}'], "Done"
else:
return f'./weights/{model}.pth', "Could not find Index file."
with gr.Blocks(theme=gr.themes.Base(), title='Mangio-RVC-Web 💻') as app:
with gr.Row():
gr.HTML(" RVC V2
")
gr.HTML(" Easy GUI coded by Rejekts ")
with gr.Tabs():
with gr.TabItem("Inference"):
# Inference Preset Row
# with gr.Row():
# mangio_preset = gr.Dropdown(label="Inference Preset", choices=sorted(get_presets()))
# mangio_preset_name_save = gr.Textbox(
# label="Your preset name"
# )
# mangio_preset_save_btn = gr.Button('Save Preset', variant="primary")
# Other RVC stuff
with gr.Row():
sid0 = gr.Dropdown(label="1.Choose your Model.", choices=sorted(names), value=check_for_name())
refresh_button = gr.Button("Refresh", variant="primary")
if check_for_name() != '':
get_vc(sorted(names)[0])
vc_transform0 = gr.Number(label="Optional: You can change the pitch here or leave it at 0.", value=0)
#clean_button = gr.Button(i18n("卸载音色省显存"), variant="primary")
spk_item = gr.Slider(
minimum=0,
maximum=2333,
step=1,
label=i18n("请选择说话人id"),
value=0,
visible=False,
interactive=True,
)
#clean_button.click(fn=clean, inputs=[], outputs=[sid0])
sid0.change(
fn=get_vc,
inputs=[sid0],
outputs=[spk_item],
)
but0 = gr.Button("Convert", variant="primary")
with gr.Row():
with gr.Column():
with gr.Row():
dropbox = gr.File(label="Drop your audio here & hit the Reload button.")
with gr.Row():
record_button=gr.Audio(source="microphone", label="OR Record audio.", type="filepath")
with gr.Row():
input_audio0 = gr.Dropdown(
label="2.Choose your audio.",
value="./audios/someguy.mp3",
choices=audio_files
)
dropbox.upload(fn=save_to_wav2, inputs=[dropbox], outputs=[input_audio0])
dropbox.upload(fn=change_choices2, inputs=[], outputs=[input_audio0])
refresh_button2 = gr.Button("Refresh", variant="primary", size='sm')
record_button.change(fn=save_to_wav, inputs=[record_button], outputs=[input_audio0])
record_button.change(fn=change_choices2, inputs=[], outputs=[input_audio0])
with gr.Row():
with gr.Accordion('Text To Speech', open=False):
with gr.Column():
lang = gr.Radio(label='Chinese & Japanese do not work with ElevenLabs currently.',choices=['en','es','fr','pt','zh-CN','de','hi','ja'], value='en')
api_box = gr.Textbox(label="Enter your API Key for ElevenLabs, or leave empty to use GoogleTTS", value='')
elevenid=gr.Dropdown(label="Voice:", choices=eleven_voices)
with gr.Column():
tfs = gr.Textbox(label="Input your Text", interactive=True, value="This is a test.")
tts_button = gr.Button(value="Speak")
tts_button.click(fn=elevenTTS, inputs=[api_box,tfs, elevenid, lang], outputs=[record_button, input_audio0])
with gr.Column():
with gr.Accordion("Index Settings", open=False):
file_index1 = gr.Dropdown(
label="3. Path to your added.index file (if it didn't automatically find it.)",
choices=get_indexes(),
value=get_index(),
interactive=True,
)
sid0.change(fn=match_index, inputs=[sid0],outputs=[file_index1])
refresh_button.click(
fn=change_choices, inputs=[], outputs=[sid0, file_index1]
)
# file_big_npy1 = gr.Textbox(
# label=i18n("特征文件路径"),
# value="E:\\codes\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
# interactive=True,
# )
index_rate1 = gr.Slider(
minimum=0,
maximum=1,
label=i18n("检索特征占比"),
value=0.66,
interactive=True,
)
vc_output2 = gr.Audio(
label="Output Audio (Click on the Three Dots in the Right Corner to Download)",
type='filepath',
interactive=False,
)
with gr.Accordion("Advanced Settings", open=False):
f0method0 = gr.Radio(
label="Optional: Change the Pitch Extraction Algorithm.\nExtraction methods are sorted from 'worst quality' to 'best quality'.\nmangio-crepe may or may not be better than rmvpe in cases where 'smoothness' is more important, but rmvpe is the best overall.",
choices=["pm", "dio", "crepe-tiny", "mangio-crepe-tiny", "crepe", "harvest", "mangio-crepe", "rmvpe"], # Fork Feature. Add Crepe-Tiny
value="rmvpe",
interactive=True,
)
crepe_hop_length = gr.Slider(
minimum=1,
maximum=512,
step=1,
label="Mangio-Crepe Hop Length. Higher numbers will reduce the chance of extreme pitch changes but lower numbers will increase accuracy. 64-192 is a good range to experiment with.",
value=120,
interactive=True,
visible=False,
)
f0method0.change(fn=whethercrepeornah, inputs=[f0method0], outputs=[crepe_hop_length])
filter_radius0 = gr.Slider(
minimum=0,
maximum=7,
label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
value=3,
step=1,
interactive=True,
)
resample_sr0 = gr.Slider(
minimum=0,
maximum=48000,
label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
value=0,
step=1,
interactive=True,
visible=False
)
rms_mix_rate0 = gr.Slider(
minimum=0,
maximum=1,
label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
value=0.21,
interactive=True,
)
protect0 = gr.Slider(
minimum=0,
maximum=0.5,
label=i18n("保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"),
value=0.33,
step=0.01,
interactive=True,
)
formanting = gr.Checkbox(
value=bool(DoFormant),
label="[EXPERIMENTAL] Formant shift inference audio",
info="Used for male to female and vice-versa conversions",
interactive=True,
visible=True,
)
formant_preset = gr.Dropdown(
value='',
choices=get_fshift_presets(),
label="browse presets for formanting",
visible=bool(DoFormant),
)
formant_refresh_button = gr.Button(
value='\U0001f504',
visible=bool(DoFormant),
variant='primary',
)
#formant_refresh_button = ToolButton( elem_id='1')
#create_refresh_button(formant_preset, lambda: {"choices": formant_preset}, "refresh_list_shiftpresets")
qfrency = gr.Slider(
value=Quefrency,
info="Default value is 1.0",
label="Quefrency for formant shifting",
minimum=0.0,
maximum=16.0,
step=0.1,
visible=bool(DoFormant),
interactive=True,
)
tmbre = gr.Slider(
value=Timbre,
info="Default value is 1.0",
label="Timbre for formant shifting",
minimum=0.0,
maximum=16.0,
step=0.1,
visible=bool(DoFormant),
interactive=True,
)
formant_preset.change(fn=preset_apply, inputs=[formant_preset, qfrency, tmbre], outputs=[qfrency, tmbre])
frmntbut = gr.Button("Apply", variant="primary", visible=bool(DoFormant))
formanting.change(fn=formant_enabled,inputs=[formanting,qfrency,tmbre,frmntbut,formant_preset,formant_refresh_button],outputs=[formanting,qfrency,tmbre,frmntbut,formant_preset,formant_refresh_button])
frmntbut.click(fn=formant_apply,inputs=[qfrency, tmbre], outputs=[qfrency, tmbre])
formant_refresh_button.click(fn=update_fshift_presets,inputs=[formant_preset, qfrency, tmbre],outputs=[formant_preset, qfrency, tmbre])
with gr.Row():
vc_output1 = gr.Textbox(label="vc_output1")
f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"), visible=False)
but0.click(
vc_single,
[
spk_item,
input_audio0,
vc_transform0,
f0_file,
f0method0,
file_index1,
# file_index2,
# file_big_npy1,
index_rate1,
filter_radius0,
resample_sr0,
rms_mix_rate0,
protect0,
crepe_hop_length
],
[vc_output1, vc_output2],
)
with gr.TabItem("Download Model"):
with gr.Row():
url=gr.Textbox(label="Enter the URL to the Model:")
with gr.Row():
model = gr.Textbox(label="Name your model:")
download_button=gr.Button("Download")
with gr.Row():
status_bar=gr.Textbox(label="")
download_button.click(fn=download_from_url, inputs=[url, model], outputs=[status_bar])
with gr.Row():
gr.Markdown(
"""
Mangio’s RVC Fork:https://github.com/Mangio621/Mangio-RVC-Fork ❤️ If you like the EasyGUI, help me keep it.❤️ https://paypal.me/lesantillan
"""
)
if warning == 'True':
app.queue(concurrency_count=511, max_size=1022).launch(share=False, quiet=True)
else:
app.queue(concurrency_count=511, max_size=1022).launch(share=True, debug=True)
#endregion