mirror of
https://github.com/svc-develop-team/so-vits-svc.git
synced 2025-01-07 03:17:31 +08:00
Add files via upload
This commit is contained in:
parent
67f358163c
commit
7e7b3a068e
65
configs/config.json
Normal file
65
configs/config.json
Normal 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
|
||||
}
|
||||
}
|
20
dataset_raw/wav_structure.txt
Normal file
20
dataset_raw/wav_structure.txt
Normal file
@ -0,0 +1,20 @@
|
||||
数据集准备
|
||||
|
||||
raw
|
||||
├───speaker0
|
||||
│ ├───xxx1-xxx1.wav
|
||||
│ ├───...
|
||||
│ └───Lxx-0xx8.wav
|
||||
└───speaker1
|
||||
├───xx2-0xxx2.wav
|
||||
├───...
|
||||
└───xxx7-xxx007.wav
|
||||
|
||||
此外还需要编辑config.json
|
||||
|
||||
"n_speakers": 10
|
||||
|
||||
"spk":{
|
||||
"speaker0": 0,
|
||||
"speaker1": 1,
|
||||
}
|
4
filelists/test.txt
Normal file
4
filelists/test.txt
Normal file
@ -0,0 +1,4 @@
|
||||
./dataset/44k/taffy/000562.wav
|
||||
./dataset/44k/nyaru/000011.wav
|
||||
./dataset/44k/nyaru/000008.wav
|
||||
./dataset/44k/taffy/000563.wav
|
15
filelists/train.txt
Normal file
15
filelists/train.txt
Normal file
@ -0,0 +1,15 @@
|
||||
./dataset/44k/taffy/000549.wav
|
||||
./dataset/44k/nyaru/000004.wav
|
||||
./dataset/44k/nyaru/000006.wav
|
||||
./dataset/44k/taffy/000551.wav
|
||||
./dataset/44k/nyaru/000009.wav
|
||||
./dataset/44k/taffy/000561.wav
|
||||
./dataset/44k/nyaru/000001.wav
|
||||
./dataset/44k/taffy/000553.wav
|
||||
./dataset/44k/nyaru/000002.wav
|
||||
./dataset/44k/taffy/000560.wav
|
||||
./dataset/44k/taffy/000557.wav
|
||||
./dataset/44k/nyaru/000005.wav
|
||||
./dataset/44k/taffy/000554.wav
|
||||
./dataset/44k/taffy/000550.wav
|
||||
./dataset/44k/taffy/000559.wav
|
4
filelists/val.txt
Normal file
4
filelists/val.txt
Normal file
@ -0,0 +1,4 @@
|
||||
./dataset/44k/nyaru/000003.wav
|
||||
./dataset/44k/nyaru/000007.wav
|
||||
./dataset/44k/taffy/000558.wav
|
||||
./dataset/44k/taffy/000556.wav
|
0
logs/44k/put_pretrained_model_here
Normal file
0
logs/44k/put_pretrained_model_here
Normal file
0
raw/put_raw_wav_here
Normal file
0
raw/put_raw_wav_here
Normal file
Loading…
Reference in New Issue
Block a user