initial upload attempt
initial upload attempt
This commit is contained in:
erew123 committed
1 parent
84c19ed5a9
commit
9fd928f6e7
527 files changed
+37359
No files matched your search
@@ -0,0 +1,170 @@
|
||||
import torch
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
version_config_list = [
|
||||
"v1/32000.json",
|
||||
"v1/40000.json",
|
||||
"v1/48000.json",
|
||||
"v2/48000.json",
|
||||
"v2/32000.json",
|
||||
]
|
||||
|
||||
|
||||
def singleton_variable(func):
|
||||
def wrapper(*args, **kwargs):
|
||||
if not wrapper.instance:
|
||||
wrapper.instance = func(*args, **kwargs)
|
||||
return wrapper.instance
|
||||
|
||||
wrapper.instance = None
|
||||
return wrapper
|
||||
|
||||
|
||||
@singleton_variable
|
||||
class Config:
|
||||
def __init__(self):
|
||||
self.device = "cuda:0"
|
||||
self.is_half = True
|
||||
self.use_jit = False
|
||||
self.n_cpu = 0
|
||||
self.gpu_name = None
|
||||
self.json_config = self.load_config_json()
|
||||
self.gpu_mem = None
|
||||
self.instead = ""
|
||||
self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
|
||||
|
||||
@staticmethod
|
||||
def load_config_json() -> dict:
|
||||
d = {}
|
||||
base_path = Path(__file__).resolve().parent
|
||||
for config_file in version_config_list:
|
||||
config_path = base_path / config_file
|
||||
with open(config_path, "r") as f:
|
||||
d[config_file] = json.load(f)
|
||||
return d
|
||||
|
||||
@staticmethod
|
||||
def has_mps() -> bool:
|
||||
if not torch.backends.mps.is_available():
|
||||
return False
|
||||
try:
|
||||
torch.zeros(1).to(torch.device("mps"))
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def has_xpu() -> bool:
|
||||
if hasattr(torch, "xpu") and torch.xpu.is_available():
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def use_fp32_config(self):
|
||||
print(
|
||||
f"Using FP32 config instead of FP16 due to GPU compatibility ({self.gpu_name})"
|
||||
)
|
||||
for config_file in version_config_list:
|
||||
config_path = os.path.join(os.getcwd(), "system", "tts_engines", "rvc", "configs", config_file)
|
||||
with open(config_path, "r") as f:
|
||||
config_data = f.read().replace("true", "false")
|
||||
with open(config_path, "w") as f:
|
||||
f.write(config_data)
|
||||
|
||||
preprocess_path = os.path.join(os.getcwd(), "system", "tts_engines", "rvc", "train", "preprocess", "preprocess.py")
|
||||
with open(preprocess_path, "r") as f:
|
||||
preprocess_data = f.read().replace("3.7", "3.0")
|
||||
with open(preprocess_path, "w") as f:
|
||||
f.write(preprocess_data)
|
||||
|
||||
def device_config(self) -> tuple:
|
||||
if torch.cuda.is_available():
|
||||
if self.has_xpu():
|
||||
self.device = self.instead = "xpu:0"
|
||||
self.is_half = True
|
||||
i_device = int(self.device.split(":")[-1])
|
||||
self.gpu_name = torch.cuda.get_device_name(i_device)
|
||||
if (
|
||||
("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
|
||||
or "P40" in self.gpu_name.upper()
|
||||
or "P10" in self.gpu_name.upper()
|
||||
or "1060" in self.gpu_name
|
||||
or "1070" in self.gpu_name
|
||||
or "1080" in self.gpu_name
|
||||
):
|
||||
self.is_half = False
|
||||
self.use_fp32_config()
|
||||
self.gpu_mem = int(
|
||||
torch.cuda.get_device_properties(i_device).total_memory
|
||||
/ 1024
|
||||
/ 1024
|
||||
/ 1024
|
||||
+ 0.4
|
||||
)
|
||||
if self.gpu_mem <= 4:
|
||||
preprocess_path = os.path.join(os.getcwd(), "system", "tts_engines", "rvc", "train", "preprocess", "preprocess.py")
|
||||
with open(preprocess_path, "r") as f:
|
||||
strr = f.read().replace("3.7", "3.0")
|
||||
with open(preprocess_path, "w") as f:
|
||||
f.write(strr)
|
||||
elif self.has_mps():
|
||||
print("No supported Nvidia GPU found")
|
||||
self.device = self.instead = "mps"
|
||||
self.is_half = False
|
||||
self.use_fp32_config()
|
||||
else:
|
||||
print("No supported Nvidia GPU found")
|
||||
self.device = self.instead = "cpu"
|
||||
self.is_half = False
|
||||
self.use_fp32_config()
|
||||
|
||||
if self.n_cpu == 0:
|
||||
self.n_cpu = os.cpu_count()
|
||||
|
||||
if self.is_half:
|
||||
x_pad = 3
|
||||
x_query = 10
|
||||
x_center = 60
|
||||
x_max = 65
|
||||
else:
|
||||
x_pad = 1
|
||||
x_query = 6
|
||||
x_center = 38
|
||||
x_max = 41
|
||||
|
||||
if self.gpu_mem is not None and self.gpu_mem <= 4:
|
||||
x_pad = 1
|
||||
x_query = 5
|
||||
x_center = 30
|
||||
x_max = 32
|
||||
|
||||
return x_pad, x_query, x_center, x_max
|
||||
|
||||
|
||||
def max_vram_gpu(gpu):
|
||||
if torch.cuda.is_available():
|
||||
gpu_properties = torch.cuda.get_device_properties(gpu)
|
||||
total_memory_gb = round(gpu_properties.total_memory / 1024 / 1024 / 1024)
|
||||
return total_memory_gb
|
||||
else:
|
||||
return "0"
|
||||
|
||||
|
||||
def get_gpu_info():
|
||||
ngpu = torch.cuda.device_count()
|
||||
gpu_infos = []
|
||||
if torch.cuda.is_available() or ngpu != 0:
|
||||
for i in range(ngpu):
|
||||
gpu_name = torch.cuda.get_device_name(i)
|
||||
mem = int(
|
||||
torch.cuda.get_device_properties(i).total_memory / 1024 / 1024 / 1024
|
||||
+ 0.4
|
||||
)
|
||||
gpu_infos.append("%s: %s %s GB" % (i, gpu_name, mem))
|
||||
if len(gpu_infos) > 0:
|
||||
gpu_info = "\n".join(gpu_infos)
|
||||
else:
|
||||
gpu_info = "Unfortunately, there is no compatible GPU available to support your training."
|
||||
return gpu_info
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"train": {
|
||||
"log_interval": 200,
|
||||
"seed": 1234,
|
||||
"epochs": 20000,
|
||||
"learning_rate": 1e-4,
|
||||
"betas": [0.8, 0.99],
|
||||
"eps": 1e-9,
|
||||
"batch_size": 4,
|
||||
"fp16_run": true,
|
||||
"lr_decay": 0.999875,
|
||||
"segment_size": 12800,
|
||||
"init_lr_ratio": 1,
|
||||
"warmup_epochs": 0,
|
||||
"c_mel": 45,
|
||||
"c_kl": 1.0
|
||||
},
|
||||
"data": {
|
||||
"max_wav_value": 32768.0,
|
||||
"sampling_rate": 32000,
|
||||
"filter_length": 1024,
|
||||
"hop_length": 320,
|
||||
"win_length": 1024,
|
||||
"n_mel_channels": 80,
|
||||
"mel_fmin": 0.0,
|
||||
"mel_fmax": null
|
||||
},
|
||||
"model": {
|
||||
"inter_channels": 192,
|
||||
"hidden_channels": 192,
|
||||
"filter_channels": 768,
|
||||
"n_heads": 2,
|
||||
"n_layers": 6,
|
||||
"kernel_size": 3,
|
||||
"p_dropout": 0,
|
||||
"resblock": "1",
|
||||
"resblock_kernel_sizes": [3,7,11],
|
||||
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
|
||||
"upsample_rates": [10,4,2,2,2],
|
||||
"upsample_initial_channel": 512,
|
||||
"upsample_kernel_sizes": [16,16,4,4,4],
|
||||
"use_spectral_norm": false,
|
||||
"gin_channels": 256,
|
||||
"spk_embed_dim": 109
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"train": {
|
||||
"log_interval": 200,
|
||||
"seed": 1234,
|
||||
"epochs": 20000,
|
||||
"learning_rate": 1e-4,
|
||||
"betas": [0.8, 0.99],
|
||||
"eps": 1e-9,
|
||||
"batch_size": 4,
|
||||
"fp16_run": true,
|
||||
"lr_decay": 0.999875,
|
||||
"segment_size": 12800,
|
||||
"init_lr_ratio": 1,
|
||||
"warmup_epochs": 0,
|
||||
"c_mel": 45,
|
||||
"c_kl": 1.0
|
||||
},
|
||||
"data": {
|
||||
"max_wav_value": 32768.0,
|
||||
"sampling_rate": 40000,
|
||||
"filter_length": 2048,
|
||||
"hop_length": 400,
|
||||
"win_length": 2048,
|
||||
"n_mel_channels": 125,
|
||||
"mel_fmin": 0.0,
|
||||
"mel_fmax": null
|
||||
},
|
||||
"model": {
|
||||
"inter_channels": 192,
|
||||
"hidden_channels": 192,
|
||||
"filter_channels": 768,
|
||||
"n_heads": 2,
|
||||
"n_layers": 6,
|
||||
"kernel_size": 3,
|
||||
"p_dropout": 0,
|
||||
"resblock": "1",
|
||||
"resblock_kernel_sizes": [3,7,11],
|
||||
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
|
||||
"upsample_rates": [10,10,2,2],
|
||||
"upsample_initial_channel": 512,
|
||||
"upsample_kernel_sizes": [16,16,4,4],
|
||||
"use_spectral_norm": false,
|
||||
"gin_channels": 256,
|
||||
"spk_embed_dim": 109
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"train": {
|
||||
"log_interval": 200,
|
||||
"seed": 1234,
|
||||
"epochs": 20000,
|
||||
"learning_rate": 1e-4,
|
||||
"betas": [0.8, 0.99],
|
||||
"eps": 1e-9,
|
||||
"batch_size": 4,
|
||||
"fp16_run": true,
|
||||
"lr_decay": 0.999875,
|
||||
"segment_size": 11520,
|
||||
"init_lr_ratio": 1,
|
||||
"warmup_epochs": 0,
|
||||
"c_mel": 45,
|
||||
"c_kl": 1.0
|
||||
},
|
||||
"data": {
|
||||
"max_wav_value": 32768.0,
|
||||
"sampling_rate": 48000,
|
||||
"filter_length": 2048,
|
||||
"hop_length": 480,
|
||||
"win_length": 2048,
|
||||
"n_mel_channels": 128,
|
||||
"mel_fmin": 0.0,
|
||||
"mel_fmax": null
|
||||
},
|
||||
"model": {
|
||||
"inter_channels": 192,
|
||||
"hidden_channels": 192,
|
||||
"filter_channels": 768,
|
||||
"n_heads": 2,
|
||||
"n_layers": 6,
|
||||
"kernel_size": 3,
|
||||
"p_dropout": 0,
|
||||
"resblock": "1",
|
||||
"resblock_kernel_sizes": [3,7,11],
|
||||
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
|
||||
"upsample_rates": [10,6,2,2,2],
|
||||
"upsample_initial_channel": 512,
|
||||
"upsample_kernel_sizes": [16,16,4,4,4],
|
||||
"use_spectral_norm": false,
|
||||
"gin_channels": 256,
|
||||
"spk_embed_dim": 109
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"train": {
|
||||
"log_interval": 200,
|
||||
"seed": 1234,
|
||||
"epochs": 20000,
|
||||
"learning_rate": 1e-4,
|
||||
"betas": [0.8, 0.99],
|
||||
"eps": 1e-9,
|
||||
"batch_size": 4,
|
||||
"fp16_run": true,
|
||||
"lr_decay": 0.999875,
|
||||
"segment_size": 12800,
|
||||
"init_lr_ratio": 1,
|
||||
"warmup_epochs": 0,
|
||||
"c_mel": 45,
|
||||
"c_kl": 1.0
|
||||
},
|
||||
"data": {
|
||||
"max_wav_value": 32768.0,
|
||||
"sampling_rate": 32000,
|
||||
"filter_length": 1024,
|
||||
"hop_length": 320,
|
||||
"win_length": 1024,
|
||||
"n_mel_channels": 80,
|
||||
"mel_fmin": 0.0,
|
||||
"mel_fmax": null
|
||||
},
|
||||
"model": {
|
||||
"inter_channels": 192,
|
||||
"hidden_channels": 192,
|
||||
"filter_channels": 768,
|
||||
"n_heads": 2,
|
||||
"n_layers": 6,
|
||||
"kernel_size": 3,
|
||||
"p_dropout": 0,
|
||||
"resblock": "1",
|
||||
"resblock_kernel_sizes": [3,7,11],
|
||||
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
|
||||
"upsample_rates": [10,8,2,2],
|
||||
"upsample_initial_channel": 512,
|
||||
"upsample_kernel_sizes": [20,16,4,4],
|
||||
"use_spectral_norm": false,
|
||||
"gin_channels": 256,
|
||||
"spk_embed_dim": 109
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"train": {
|
||||
"log_interval": 200,
|
||||
"seed": 1234,
|
||||
"epochs": 20000,
|
||||
"learning_rate": 1e-4,
|
||||
"betas": [0.8, 0.99],
|
||||
"eps": 1e-9,
|
||||
"batch_size": 4,
|
||||
"fp16_run": true,
|
||||
"lr_decay": 0.999875,
|
||||
"segment_size": 17280,
|
||||
"init_lr_ratio": 1,
|
||||
"warmup_epochs": 0,
|
||||
"c_mel": 45,
|
||||
"c_kl": 1.0
|
||||
},
|
||||
"data": {
|
||||
"max_wav_value": 32768.0,
|
||||
"sampling_rate": 48000,
|
||||
"filter_length": 2048,
|
||||
"hop_length": 480,
|
||||
"win_length": 2048,
|
||||
"n_mel_channels": 128,
|
||||
"mel_fmin": 0.0,
|
||||
"mel_fmax": null
|
||||
},
|
||||
"model": {
|
||||
"inter_channels": 192,
|
||||
"hidden_channels": 192,
|
||||
"filter_channels": 768,
|
||||
"n_heads": 2,
|
||||
"n_layers": 6,
|
||||
"kernel_size": 3,
|
||||
"p_dropout": 0,
|
||||
"resblock": "1",
|
||||
"resblock_kernel_sizes": [3,7,11],
|
||||
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
|
||||
"upsample_rates": [12,10,2,2],
|
||||
"upsample_initial_channel": 512,
|
||||
"upsample_kernel_sizes": [24,20,4,4],
|
||||
"use_spectral_norm": false,
|
||||
"gin_channels": 256,
|
||||
"spk_embed_dim": 109
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user