Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +128 -0
- configs/s1.yaml +69 -0
- configs/s2.json +62 -0
- data8/phoneme.txt +0 -0
- data8/semantic.tsv +0 -0
- data8/wavs/6.wav +3 -0
- data8/wavs/609.wav +3 -0
- data8/wavs/610.wav +3 -0
- data8/wavs/611.wav +3 -0
- data8/wavs/613.wav +3 -0
- data8/wavs/615.wav +3 -0
- data8/wavs/616.wav +3 -0
- data8/wavs/618.wav +3 -0
- data8/wavs/62.wav +3 -0
- data8/wavs/628.wav +3 -0
- data8/wavs/629.wav +3 -0
- data8/wavs/63.wav +3 -0
- data8/wavs/630.wav +3 -0
- data8/wavs/631.wav +3 -0
- data8/wavs/634.wav +3 -0
- data8/wavs/637.wav +3 -0
- data8/wavs/639.wav +3 -0
- data8/wavs/64.wav +3 -0
- data8/wavs/640.wav +3 -0
- data8/wavs/641.wav +3 -0
- data8/wavs/642.wav +3 -0
- data8/wavs/643.wav +3 -0
- data8/wavs/644.wav +3 -0
- data8/wavs/649.wav +3 -0
- data8/wavs/650.wav +3 -0
- data8/wavs/651.wav +3 -0
- data8/wavs/653.wav +3 -0
- data8/wavs/654.wav +3 -0
- data8/wavs/655.wav +3 -0
- data8/wavs/656.wav +3 -0
- data8/wavs/657.wav +3 -0
- data8/wavs/658.wav +3 -0
- data8/wavs/659.wav +3 -0
- data8/wavs/66.wav +3 -0
- data8/wavs/661.wav +3 -0
- data8/wavs/662.wav +3 -0
- data8/wavs/663.wav +3 -0
- data8/wavs/664.wav +3 -0
- data8/wavs/665.wav +3 -0
- data8/wavs/666.wav +3 -0
- data8/wavs/667.wav +3 -0
- data8/wavs/669.wav +3 -0
- data8/wavs/67.wav +3 -0
- data8/wavs/670.wav +3 -0
- data8/wavs/673.wav +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,131 @@ 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 |
+
data8/wavs/721.wav filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
data8/wavs/75.wav filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
data8/wavs/726.wav filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
data8/wavs/72.wav filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
data8/wavs/712.wav filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
data8/wavs/718.wav filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
data8/wavs/79.wav filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
data8/wavs/97.wav filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
data8/wavs/89.wav filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
data8/wavs/81.wav filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
data8/wavs/99.wav filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
data8/wavs/717.wav filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
data8/wavs/689.wav filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
data8/wavs/714.wav filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
data8/wavs/713.wav filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
data8/wavs/707.wav filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
data8/wavs/706.wav filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
data8/wavs/87.wav filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
data8/wavs/78.wav filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
data8/wavs/71.wav filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
data8/wavs/693.wav filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
data8/wavs/708.wav filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
data8/wavs/711.wav filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
data8/wavs/96.wav filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
data8/wavs/698.wav filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
data8/wavs/705.wav filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
data8/wavs/659.wav filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
data8/wavs/696.wav filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
data8/wavs/650.wav filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
data8/wavs/83.wav filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
data8/wavs/649.wav filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
data8/wavs/699.wav filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
data8/wavs/692.wav filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
data8/wavs/691.wav filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
data8/wavs/90.wav filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
data8/wavs/93.wav filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
data8/wavs/723.wav filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
data8/wavs/700.wav filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
data8/wavs/85.wav filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
data8/wavs/703.wav filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
data8/wavs/694.wav filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
data8/wavs/685.wav filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
data8/wavs/68.wav filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
data8/wavs/86.wav filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
data8/wavs/88.wav filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
data8/wavs/76.wav filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
data8/wavs/686.wav filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
data8/wavs/98.wav filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
data8/wavs/80.wav filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
data8/wavs/716.wav filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
data8/wavs/663.wav filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
data8/wavs/701.wav filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
data8/wavs/640.wav filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
data8/wavs/720.wav filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
data8/wavs/73.wav filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
data8/wavs/67.wav filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
data8/wavs/674.wav filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
data8/wavs/664.wav filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
data8/wavs/695.wav filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
data8/wavs/702.wav filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
data8/wavs/7.wav filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
data8/wavs/677.wav filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
data8/wavs/697.wav filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
data8/wavs/644.wav filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
data8/wavs/679.wav filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
data8/wavs/94.wav filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
data8/wavs/688.wav filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
data8/wavs/70.wav filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
data8/wavs/8.wav filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
data8/wavs/657.wav filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
data8/wavs/655.wav filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
data8/wavs/670.wav filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
data8/wavs/719.wav filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
data8/wavs/690.wav filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
data8/wavs/724.wav filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
data8/wavs/651.wav filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
data8/wavs/631.wav filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
data8/wavs/683.wav filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
data8/wavs/69.wav filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
data8/wavs/725.wav filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
data8/wavs/665.wav filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
data8/wavs/641.wav filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
data8/wavs/66.wav filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
data8/wavs/91.wav filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
data8/wavs/9.wav filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
data8/wavs/654.wav filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
data8/wavs/92.wav filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
data8/wavs/669.wav filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
data8/wavs/628.wav filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
data8/wavs/74.wav filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
data8/wavs/63.wav filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
data8/wavs/682.wav filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
data8/wavs/709.wav filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
data8/wavs/722.wav filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
data8/wavs/639.wav filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
data8/wavs/630.wav filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
data8/wavs/616.wav filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
data8/wavs/610.wav filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
data8/wavs/658.wav filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
data8/wavs/661.wav filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
data8/wavs/673.wav filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
data8/wavs/643.wav filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
data8/wavs/680.wav filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
data8/wavs/667.wav filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
data8/wavs/662.wav filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
data8/wavs/656.wav filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
data8/wavs/710.wav filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
data8/wavs/613.wav filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
data8/wavs/642.wav filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
data8/wavs/653.wav filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
data8/wavs/684.wav filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
data8/wavs/629.wav filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
data8/wavs/637.wav filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
data8/wavs/84.wav filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
data8/wavs/618.wav filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
data8/wavs/95.wav filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
data8/wavs/675.wav filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
data8/wavs/62.wav filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
data8/wavs/666.wav filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
data8/wavs/609.wav filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
data8/wavs/611.wav filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
data8/wavs/615.wav filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
data8/wavs/676.wav filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
data8/wavs/64.wav filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
data8/wavs/634.wav filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
data8/wavs/6.wav filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
data8/wavs/77.wav filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
data8/wavs/678.wav filter=lfs diff=lfs merge=lfs -text
|
configs/s1.yaml
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
output_dir: "logs/s1"
|
| 2 |
+
train:
|
| 3 |
+
seed: 1234
|
| 4 |
+
epochs: 15
|
| 5 |
+
batch_size: 8
|
| 6 |
+
save_every_n_epoch: 5
|
| 7 |
+
precision: 32
|
| 8 |
+
if_save_latest: true
|
| 9 |
+
if_save_every_weights: true
|
| 10 |
+
exp_name: "gpt_training"
|
| 11 |
+
half_weights_save_dir: "weights/s1"
|
| 12 |
+
wandb:
|
| 13 |
+
project: "gpt-sovits-hindi"
|
| 14 |
+
name: "stage1_training"
|
| 15 |
+
entity: null
|
| 16 |
+
log_interval: 100
|
| 17 |
+
|
| 18 |
+
optimizer:
|
| 19 |
+
lr_init: 0.0001
|
| 20 |
+
lr: 0.0004
|
| 21 |
+
lr_end: 0.00001
|
| 22 |
+
warmup_steps: 500
|
| 23 |
+
decay_steps: 1000
|
| 24 |
+
|
| 25 |
+
data:
|
| 26 |
+
training_files: "data8"
|
| 27 |
+
max_sec: 60
|
| 28 |
+
max_frames: 60
|
| 29 |
+
filter_length: 2048
|
| 30 |
+
hop_length: 640
|
| 31 |
+
win_length: 2048
|
| 32 |
+
mel_channels: 128
|
| 33 |
+
mel_fmin: 0.0
|
| 34 |
+
mel_fmax: null
|
| 35 |
+
cleaned_text: true
|
| 36 |
+
num_workers: 4
|
| 37 |
+
batch_size: 8
|
| 38 |
+
pad_val: 1024
|
| 39 |
+
|
| 40 |
+
# Data paths
|
| 41 |
+
train_semantic_path: "data8/semantic.tsv"
|
| 42 |
+
train_phoneme_path: "data8/phoneme.txt"
|
| 43 |
+
|
| 44 |
+
model:
|
| 45 |
+
hidden_dim: 768
|
| 46 |
+
embedding_dim: 768
|
| 47 |
+
n_layer: 12
|
| 48 |
+
head: 12
|
| 49 |
+
n_embd: 768
|
| 50 |
+
vocab_size: 2048
|
| 51 |
+
block_size: 1000
|
| 52 |
+
embd_pdrop: 0.1
|
| 53 |
+
resid_pdrop: 0.1
|
| 54 |
+
attn_pdrop: 0.1
|
| 55 |
+
semantic_dim: 1024
|
| 56 |
+
num_layers: 6
|
| 57 |
+
ffn_hidden: 3072
|
| 58 |
+
dropout: 0.1
|
| 59 |
+
attention_dropout: 0.1
|
| 60 |
+
hidden_dropout: 0.1
|
| 61 |
+
max_text_positions: 2048
|
| 62 |
+
max_mel_positions: 8000
|
| 63 |
+
prenet_dim: 384
|
| 64 |
+
postnet_dim: 384
|
| 65 |
+
prenet_layers: 3
|
| 66 |
+
postnet_layers: 3
|
| 67 |
+
phoneme_vocab_size: 2048
|
| 68 |
+
EOS: 2047
|
| 69 |
+
pad_val: 1024
|
configs/s2.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"log_interval": 100,
|
| 4 |
+
"eval_interval": 500,
|
| 5 |
+
"seed": 1234,
|
| 6 |
+
"epochs": 100,
|
| 7 |
+
"learning_rate": 0.0001,
|
| 8 |
+
"betas": [0.8, 0.99],
|
| 9 |
+
"eps": 1e-09,
|
| 10 |
+
"batch_size": 32,
|
| 11 |
+
"fp16_run": true,
|
| 12 |
+
"lr_decay": 0.999875,
|
| 13 |
+
"segment_size": 20480,
|
| 14 |
+
"init_lr_ratio": 1,
|
| 15 |
+
"warmup_epochs": 0,
|
| 16 |
+
"c_mel": 45,
|
| 17 |
+
"c_kl": 1.0,
|
| 18 |
+
"text_low_lr_rate": 0.4,
|
| 19 |
+
"gpu_numbers": "0"
|
| 20 |
+
},
|
| 21 |
+
"data": {
|
| 22 |
+
"max_wav_value": 32768.0,
|
| 23 |
+
"sampling_rate": 32000,
|
| 24 |
+
"filter_length": 2048,
|
| 25 |
+
"hop_length": 640,
|
| 26 |
+
"win_length": 2048,
|
| 27 |
+
"n_mel_channels": 128,
|
| 28 |
+
"mel_fmin": 0.0,
|
| 29 |
+
"mel_fmax": null,
|
| 30 |
+
"add_blank": true,
|
| 31 |
+
"n_speakers": 300,
|
| 32 |
+
"cleaned_text": true,
|
| 33 |
+
"training_files": "data8",
|
| 34 |
+
"exp_dir": "/workspace/GPT-SoVITS/logs/s2"
|
| 35 |
+
},
|
| 36 |
+
"model": {
|
| 37 |
+
"inter_channels": 192,
|
| 38 |
+
"hidden_channels": 192,
|
| 39 |
+
"filter_channels": 768,
|
| 40 |
+
"n_heads": 2,
|
| 41 |
+
"n_layers": 6,
|
| 42 |
+
"kernel_size": 3,
|
| 43 |
+
"p_dropout": 0.1,
|
| 44 |
+
"resblock": "1",
|
| 45 |
+
"resblock_kernel_sizes": [3, 7, 11],
|
| 46 |
+
"resblock_dilation_sizes": [
|
| 47 |
+
[1, 3, 5],
|
| 48 |
+
[1, 3, 5],
|
| 49 |
+
[1, 3, 5]
|
| 50 |
+
],
|
| 51 |
+
"upsample_rates": [10, 8, 2, 2, 2],
|
| 52 |
+
"upsample_initial_channel": 512,
|
| 53 |
+
"upsample_kernel_sizes": [16, 16, 8, 2, 2],
|
| 54 |
+
"n_layers_q": 3,
|
| 55 |
+
"use_spectral_norm": false,
|
| 56 |
+
"gin_channels": 512,
|
| 57 |
+
"semantic_frame_rate": "25hz",
|
| 58 |
+
"freeze_quantizer": true
|
| 59 |
+
},
|
| 60 |
+
"s2_ckpt_dir": "/workspace/GPT-SoVITS/logs/s2/sovits_training",
|
| 61 |
+
"content_module": "cnhubert"
|
| 62 |
+
}
|
data8/phoneme.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
data8/semantic.tsv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
data8/wavs/6.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:293b31a9dcd9685dd6998dd9dde7994098a742862d5cd4d222775f15ea022223
|
| 3 |
+
size 4292686
|
data8/wavs/609.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4aaf028b185d6face47495f34e4fad1743d4c0da3ee9325d9c11e9b12fe87f7
|
| 3 |
+
size 4735054
|
data8/wavs/610.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:888d4304a3b73f0c7b92072c5b52005fbad725be625f63ddac8aaba8c3b3487d
|
| 3 |
+
size 4177998
|
data8/wavs/611.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0398315decd36d1f3ea049a59df96933d7f01deae0ffc58bfcb2fb1e168d652
|
| 3 |
+
size 4407374
|
data8/wavs/613.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66600c34f01fbd13d67ea64986775ff9f3c7f6141c4a60d2959dc313ab440225
|
| 3 |
+
size 4751438
|
data8/wavs/615.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:937a250830a461c4e61a882b4fad85f285e917a52d741f3ef5e807f198b6bc70
|
| 3 |
+
size 4440142
|
data8/wavs/616.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e286ac0cc9a409004671a29db33a3f4fcbf31baeca0b728d0509d6e8ca4eab3
|
| 3 |
+
size 4571214
|
data8/wavs/618.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f1ed410246552b54203060d7e0645dda1d15af9820f2f906bd586d913e519dc
|
| 3 |
+
size 4341838
|
data8/wavs/62.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa6ad46f60d318b4f7f0ee710dbbb716298ad0aa2f3eed0b17d237d4bf1e6959
|
| 3 |
+
size 4390990
|
data8/wavs/628.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3370971f943f485d4d5315081535575c2eecff373d1f26b2291bc5d11462dde0
|
| 3 |
+
size 4423758
|
data8/wavs/629.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2ca5bd2daa437576c0220a40f4a06e49111239695d8bc7036647c948eeb37e5
|
| 3 |
+
size 4554830
|
data8/wavs/63.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e981a415b44939cc103238bf5256a621223b2e29ae7d044642cc474bd0d52e73
|
| 3 |
+
size 4702286
|
data8/wavs/630.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36def8a5837a0d8ab60924dabe433454a204d56d510c50022a9dbb5a36846d73
|
| 3 |
+
size 4407374
|
data8/wavs/631.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c408ab7603b0dd1b1ccac0f6b8e1eadced21912b226bf7e74e42fa0921ca6a8
|
| 3 |
+
size 4292686
|
data8/wavs/634.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d1b83882671e7d61263735b73e1493b684ddfee96b62b42dac8295f3093228f
|
| 3 |
+
size 4800590
|
data8/wavs/637.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:987d39bf0d984f6ffa5ae3718b2ee9c35a1b24cea8ed4dfb4982ffd656e2981f
|
| 3 |
+
size 4440142
|
data8/wavs/639.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e479cfd142647495b641a734cd91dca3daac8332d482d97dab1b25063c2e4e25
|
| 3 |
+
size 4554830
|
data8/wavs/64.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603f0668ed80df9c2b2aa61197f91bd4409e8af8a88322088265cb7096c56867
|
| 3 |
+
size 4259918
|
data8/wavs/640.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:479c086c6023d7f26ce749bc4fda1a1cbbf79ded1848baf96cb827af89324750
|
| 3 |
+
size 4358222
|
data8/wavs/641.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aab35b4d3ea2ddfca11c5d8b5bb2c390012cb9141487da65c81a2b2f78cf45cb
|
| 3 |
+
size 4292686
|
data8/wavs/642.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ac9fdd825001ea307d2aeba6f807f39460c57e7cdb058deef161c2f0826aba
|
| 3 |
+
size 4718670
|
data8/wavs/643.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34cd66dff1f490939f054b075e74a0283afa31a4191bbe77aec7975252dcb27b
|
| 3 |
+
size 4751438
|
data8/wavs/644.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:244c96f2c62c3b61e3c93bf5b4ba271db3cf4750bbd7bd051ba8af2dd0c4532b
|
| 3 |
+
size 4309070
|
data8/wavs/649.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbacdb82360b68676b9ad575fc0a0f46bd477100a3c589db5dcd9a6f38f5de59
|
| 3 |
+
size 4653134
|
data8/wavs/650.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5812b9c530c1cd59987310de5606cf8c8eebd97d8aa6393072e8a0c59a436fdb
|
| 3 |
+
size 4440142
|
data8/wavs/651.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15faa1cf9e588cb030ca0d18bd0c80ddc76a1294ac32660f4f68e746ff85d759
|
| 3 |
+
size 4800590
|
data8/wavs/653.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b468effa901a08130e75fe7bf0e2b345977ef4f851e2678b8c7aaef03394c31
|
| 3 |
+
size 4489294
|
data8/wavs/654.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b22a2ad47e6435a120b947adbf6ac41a656bf2569a3942e990a5988004fed53
|
| 3 |
+
size 4653134
|
data8/wavs/655.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507529f46ccf17b0ed31e8f44796673ed9541c7da0a7f7041b4fe56288d5a961
|
| 3 |
+
size 4571214
|
data8/wavs/656.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31f519d25b73fa28c878b2c3cb81b329b5a2e4f56d3c5aab2d26a749bd70df91
|
| 3 |
+
size 4505678
|
data8/wavs/657.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d9c9451a304bb79af40f4683489b483e6067ba69c882815edd24c32a70a0cad
|
| 3 |
+
size 4538446
|
data8/wavs/658.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8f42e06827965d267d28605c48adfcd143b7a993558edc6ce3658d6d25a6533
|
| 3 |
+
size 4423758
|
data8/wavs/659.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e4a576ad38e3612465ded6e6d5ca7c22431bc2aaf44f26c0b0512cfaf99b3ea
|
| 3 |
+
size 4292686
|
data8/wavs/66.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb02eb1e680cf897231953c7fe2594289ff56dd029d2745b0a898e2de55f6966
|
| 3 |
+
size 4358222
|
data8/wavs/661.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde27dae7c9d178335820b741b6adf7e669224dfb1aa7a8065c62d17eaff4f2f
|
| 3 |
+
size 4685902
|
data8/wavs/662.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:017c7413503eb83e3154a608486bdd7116a9fe8f98fe24e53b4eb066dd42fa9a
|
| 3 |
+
size 4735054
|
data8/wavs/663.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b591fdc35307265e1b6b70d825760a3c3f9127b4ddc1f9e880d098e6eb2b68a7
|
| 3 |
+
size 4800590
|
data8/wavs/664.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fd20948112304a10e7c07b3ed53cbfa0edda1cba2eeca0e188ff3de673a2b42
|
| 3 |
+
size 4538446
|
data8/wavs/665.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8f2ab7a5d9e0b09bda73743b08817cdb8dbb25c7cfb4eb848a03b0a99d9487d
|
| 3 |
+
size 4505678
|
data8/wavs/666.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c14780aa7c81d553c9bb2375bf110e09f3be6a221708e96a2fd75fd92b0a6de
|
| 3 |
+
size 4341838
|
data8/wavs/667.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68afe49641bf4a7cad2933659a5f071b28028b065eb1938f920d2d4bc69b689
|
| 3 |
+
size 4276302
|
data8/wavs/669.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85a36f4d15e22874a0930aa71b59ed08fbd5d67e20a33a751244e52eb5e5b596
|
| 3 |
+
size 4620366
|
data8/wavs/67.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66929c24a7a919080da135639706803fe7676bcb53b776d226dd554f061fdd09
|
| 3 |
+
size 4341838
|
data8/wavs/670.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03ce4a818e7a1cf1a9a2a2c492aef9f17f05d2fcdde57a36b0af932f74ac538d
|
| 3 |
+
size 4603982
|
data8/wavs/673.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf41ed0ad2b7a36b0188bc5b012ab9337acbfe64151cf53ceadb19104b8ce3c0
|
| 3 |
+
size 4767822
|