WindyMadman/so-vits-svc
1
0
Fork 0
mirror of https://github.com/svc-develop-team/so-vits-svc.git synced 2025-01-08 11:57:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

Increase convenience for colab training

Browse Source
This commit is contained in:
謬紗特 2023-03-12 00:07:29 +08:00 committed by GitHub
parent 30388ce3a8
commit ab962d4112
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 66 additions and 66 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
configs/config.json
View File

@ -1,65 +0,0 @@
{
"train": {
"log_interval": 200,
"eval_interval": 800,
"seed": 1234,
"epochs": 10000,
"learning_rate": 0.0001,
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"batch_size": 6,
"fp16_run": false,
"lr_decay": 0.999875,
"segment_size": 10240,
"init_lr_ratio": 1,
"warmup_epochs": 0,
"c_mel": 45,
"c_kl": 1.0,
"use_sr": true,
"max_speclen": 512,
"port": "8001",
"keep_ckpts": 3
},
"data": {
"training_files": "filelists/train.txt",
"validation_files": "filelists/val.txt",
"max_wav_value": 32768.0,
"sampling_rate": 44100,
"filter_length": 2048,
"hop_length": 512,
"win_length": 2048,
"n_mel_channels": 80,
"mel_fmin": 0.0,
"mel_fmax": 22050
},
"model": {
"inter_channels": 192,
"hidden_channels": 192,
"filter_channels": 768,
"n_heads": 2,
"n_layers": 6,
"kernel_size": 3,
"p_dropout": 0.1,
"resblock": "1",
"resblock_kernel_sizes": [3,7,11],
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
"upsample_rates": [ 8, 8, 2, 2, 2],
"upsample_initial_channel": 512,
"upsample_kernel_sizes": [16,16, 4, 4, 4],
"n_layers_q": 3,
"use_spectral_norm": false,
"gin_channels": 256,
"ssl_dim": 256,
"n_speakers": 200
},
"spk": {
"nyaru": 0,
"huiyu": 1,
"nen": 2,
"paimon": 3,
"yunhao": 4
}
}

65
configs_template/config_template.json Normal file
View File

@ -0,0 +1,65 @@
{
"train": {
"log_interval": 200,
"eval_interval": 800,
"seed": 1234,
"epochs": 10000,
"learning_rate": 0.0001,
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"batch_size": 6,
"fp16_run": false,
"lr_decay": 0.999875,
"segment_size": 10240,
"init_lr_ratio": 1,
"warmup_epochs": 0,
"c_mel": 45,
"c_kl": 1.0,
"use_sr": true,
"max_speclen": 512,
"port": "8001",
"keep_ckpts": 3
},
"data": {
"training_files": "filelists/train.txt",
"validation_files": "filelists/val.txt",
"max_wav_value": 32768.0,
"sampling_rate": 44100,
"filter_length": 2048,
"hop_length": 512,
"win_length": 2048,
"n_mel_channels": 80,
"mel_fmin": 0.0,
"mel_fmax": 22050
},
"model": {
"inter_channels": 192,
"hidden_channels": 192,
"filter_channels": 768,
"n_heads": 2,
"n_layers": 6,
"kernel_size": 3,
"p_dropout": 0.1,
"resblock": "1",
"resblock_kernel_sizes": [3,7,11],
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
"upsample_rates": [ 8, 8, 2, 2, 2],
"upsample_initial_channel": 512,
"upsample_kernel_sizes": [16,16, 4, 4, 4],
"n_layers_q": 3,
"use_spectral_norm": false,
"gin_channels": 256,
"ssl_dim": 256,
"n_speakers": 200
},
"spk": {
"nyaru": 0,
"huiyu": 1,
"nen": 2,
"paimon": 3,
"yunhao": 4
}
}

2
preprocess_flist_config.py
View File

@ -7,7 +7,7 @@ from random import shuffle
import json
import wave
config_template = json.load(open("configs/config.json"))
config_template = json.load(open("configs_template/config_template.json"))
pattern = re.compile(r'^[\.a-zA-Z0-9_\/]+$')