Hugging Face's logo

PluginsKers
/
Convbased-Studio

PyTorch
Chinese
English
speech-synthesis
speech-to-speech
voice-conversion
audio
chinese-tts
multi-speaker
convolution
encoder-decoder
Model card Files
xet
Community
2
PluginsKers commited on
Commit
6cbfd2c
·
verified ·
1 Parent(s): 1f6cf4c

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. chinese-hubert-base/HiFiGAN/config.json +46 -0
  2. chinese-hubert-base/HiFiGAN/f0D48k.pth +3 -0
  3. chinese-hubert-base/HiFiGAN/f0G48k.pth +3 -0
  4. contentvec/HiFiGAN/476sid/config.json +46 -0
  5. contentvec/HiFiGAN/476sid/f0D48k.pth +3 -0
  6. contentvec/HiFiGAN/476sid/f0G48k.pth +3 -0
  7. contentvec/SIFiGAN/config.json +46 -0
  8. contentvec/SIFiGAN/f0D48k.pth +3 -0
  9. contentvec/SIFiGAN/f0G48k.pth +3 -0
  10. spin-v2/BigVGAN/40k/D_181080.pth +3 -0
  11. spin-v2/BigVGAN/40k/G_181080.pth +3 -0
  12. spin/HiFiGAN/config.json +46 -0
  13. spin/HiFiGAN/f0D48k.pth +3 -0
  14. spin/HiFiGAN/f0G48k.pth +3 -0
  15. spin/SiFiGAN/config.json +46 -0
  16. spin/SiFiGAN/f0D48k.pth +3 -0
  17. spin/SiFiGAN/f0G48k.pth +3 -0
chinese-hubert-base/HiFiGAN/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "learning_rate": 0.0001,
6
+ "betas": [0.8, 0.99],
7
+ "eps": 1e-9,
8
+ "lr_decay": 0.999875,
9
+ "segment_size": 17280,
10
+ "c_mel": 45,
11
+ "c_kl": 1.0
12
+ },
13
+ "data": {
14
+ "max_wav_value": 32768.0,
15
+ "sample_rate": 48000,
16
+ "filter_length": 2048,
17
+ "hop_length": 480,
18
+ "win_length": 2048,
19
+ "n_mel_channels": 128,
20
+ "mel_fmin": 0.0,
21
+ "mel_fmax": null
22
+ },
23
+ "model": {
24
+ "inter_channels": 192,
25
+ "hidden_channels": 192,
26
+ "filter_channels": 768,
27
+ "text_enc_hidden_dim": 768,
28
+ "n_heads": 2,
29
+ "n_layers": 6,
30
+ "kernel_size": 3,
31
+ "p_dropout": 0,
32
+ "resblock": "1",
33
+ "resblock_kernel_sizes": [3, 7, 11],
34
+ "resblock_dilation_sizes": [
35
+ [1, 3, 5],
36
+ [1, 3, 5],
37
+ [1, 3, 5]
38
+ ],
39
+ "upsample_rates": [12, 10, 2, 2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [24, 20, 4, 4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
chinese-hubert-base/HiFiGAN/f0D48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9410083f8dbab4d886f4aaaaf09db0cfa069009b008d15fbb83c2d4c9bfb01
3
+ size 285696040
chinese-hubert-base/HiFiGAN/f0G48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9534f60010c4db7ceb9d3f02ea1c065d2101bfed6c830be633114a8794aa5916
3
+ size 150735634
contentvec/HiFiGAN/476sid/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "learning_rate": 1e-4,
6
+ "betas": [0.8, 0.99],
7
+ "eps": 1e-9,
8
+ "lr_decay": 0.999875,
9
+ "segment_size": 17280,
10
+ "c_mel": 45,
11
+ "c_kl": 1.0
12
+ },
13
+ "data": {
14
+ "max_wav_value": 32768.0,
15
+ "sample_rate": 48000,
16
+ "filter_length": 2048,
17
+ "hop_length": 480,
18
+ "win_length": 2048,
19
+ "n_mel_channels": 128,
20
+ "mel_fmin": 0.0,
21
+ "mel_fmax": null
22
+ },
23
+ "model": {
24
+ "inter_channels": 192,
25
+ "hidden_channels": 192,
26
+ "filter_channels": 768,
27
+ "text_enc_hidden_dim": 768,
28
+ "n_heads": 2,
29
+ "n_layers": 6,
30
+ "kernel_size": 3,
31
+ "p_dropout": 0,
32
+ "resblock": "1",
33
+ "resblock_kernel_sizes": [3, 7, 11],
34
+ "resblock_dilation_sizes": [
35
+ [1, 3, 5],
36
+ [1, 3, 5],
37
+ [1, 3, 5]
38
+ ],
39
+ "upsample_rates": [12, 10, 2, 2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [24, 20, 4, 4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 476
45
+ }
46
+ }
contentvec/HiFiGAN/476sid/f0D48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c8a6730363c5ce6890b55ace3117ced9a0718d49500b8a12738fb6ae250e1e
3
+ size 285697566
contentvec/HiFiGAN/476sid/f0G48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd018b82e685e8ba8b818bbf2e10e6879b1d8637d04168aed555d53e75fbf681
3
+ size 151115402
contentvec/SIFiGAN/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "learning_rate": 0.0001,
6
+ "betas": [0.8, 0.99],
7
+ "eps": 1e-9,
8
+ "lr_decay": 0.999875,
9
+ "segment_size": 17280,
10
+ "c_mel": 45,
11
+ "c_kl": 1.0
12
+ },
13
+ "data": {
14
+ "max_wav_value": 32768.0,
15
+ "sample_rate": 48000,
16
+ "filter_length": 2048,
17
+ "hop_length": 480,
18
+ "win_length": 2048,
19
+ "n_mel_channels": 128,
20
+ "mel_fmin": 0.0,
21
+ "mel_fmax": null
22
+ },
23
+ "model": {
24
+ "inter_channels": 192,
25
+ "hidden_channels": 192,
26
+ "filter_channels": 768,
27
+ "text_enc_hidden_dim": 768,
28
+ "n_heads": 2,
29
+ "n_layers": 6,
30
+ "kernel_size": 3,
31
+ "p_dropout": 0,
32
+ "resblock": "1",
33
+ "resblock_kernel_sizes": [3, 7, 11],
34
+ "resblock_dilation_sizes": [
35
+ [1, 3, 5],
36
+ [1, 3, 5],
37
+ [1, 3, 5]
38
+ ],
39
+ "upsample_rates": [12, 10, 2, 2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [24, 20, 4, 4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
contentvec/SIFiGAN/f0D48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:112782860a879cfa859e3ac44c0c6edead7f338bc2890d96e90270103032b65c
3
+ size 285691018
contentvec/SIFiGAN/f0G48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe340981cbd32ab1a95d395bd9a0c3c16887bb525c84120f0993de3c817bb80
3
+ size 171331737
spin-v2/BigVGAN/40k/D_181080.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00de03e097574f2b2db5aee33c1a0052456437c00aef0101d5175240cf5ecbe0
3
+ size 857123185
spin-v2/BigVGAN/40k/G_181080.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b359040cd054fb0a1a8360a15a341582692b4efe7bfb39c6de7a5e2126b7f22d
3
+ size 438608285
spin/HiFiGAN/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "learning_rate": 0.0001,
6
+ "betas": [0.8, 0.99],
7
+ "eps": 1e-9,
8
+ "lr_decay": 0.999875,
9
+ "segment_size": 17280,
10
+ "c_mel": 45,
11
+ "c_kl": 1.0
12
+ },
13
+ "data": {
14
+ "max_wav_value": 32768.0,
15
+ "sample_rate": 48000,
16
+ "filter_length": 2048,
17
+ "hop_length": 480,
18
+ "win_length": 2048,
19
+ "n_mel_channels": 128,
20
+ "mel_fmin": 0.0,
21
+ "mel_fmax": null
22
+ },
23
+ "model": {
24
+ "inter_channels": 192,
25
+ "hidden_channels": 192,
26
+ "filter_channels": 768,
27
+ "text_enc_hidden_dim": 768,
28
+ "n_heads": 2,
29
+ "n_layers": 6,
30
+ "kernel_size": 3,
31
+ "p_dropout": 0,
32
+ "resblock": "1",
33
+ "resblock_kernel_sizes": [3, 7, 11],
34
+ "resblock_dilation_sizes": [
35
+ [1, 3, 5],
36
+ [1, 3, 5],
37
+ [1, 3, 5]
38
+ ],
39
+ "upsample_rates": [12, 10, 2, 2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [24, 20, 4, 4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
spin/HiFiGAN/f0D48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b404aaa6ef198f2e2eaa9f21af52e59336643e52b8783b056cdfbf958e2f719
3
+ size 285690687
spin/HiFiGAN/f0G48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6a4340c0081afe020b308e2e5b110ebfab2ab573f7c35849a8a39fd75b2f9a
3
+ size 150729246
spin/SiFiGAN/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "learning_rate": 0.0001,
6
+ "betas": [0.8, 0.99],
7
+ "eps": 1e-9,
8
+ "lr_decay": 0.999875,
9
+ "segment_size": 17280,
10
+ "c_mel": 45,
11
+ "c_kl": 1.0
12
+ },
13
+ "data": {
14
+ "max_wav_value": 32768.0,
15
+ "sample_rate": 48000,
16
+ "filter_length": 2048,
17
+ "hop_length": 480,
18
+ "win_length": 2048,
19
+ "n_mel_channels": 128,
20
+ "mel_fmin": 0.0,
21
+ "mel_fmax": null
22
+ },
23
+ "model": {
24
+ "inter_channels": 192,
25
+ "hidden_channels": 192,
26
+ "filter_channels": 768,
27
+ "text_enc_hidden_dim": 768,
28
+ "n_heads": 2,
29
+ "n_layers": 6,
30
+ "kernel_size": 3,
31
+ "p_dropout": 0,
32
+ "resblock": "1",
33
+ "resblock_kernel_sizes": [3, 7, 11],
34
+ "resblock_dilation_sizes": [
35
+ [1, 3, 5],
36
+ [1, 3, 5],
37
+ [1, 3, 5]
38
+ ],
39
+ "upsample_rates": [12, 10, 2, 2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [24, 20, 4, 4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
spin/SiFiGAN/f0D48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbc8d5cf0f682c62f276cd921946d05493af13b49c51a0a4e6c4df075eaf85c
3
+ size 285690687
spin/SiFiGAN/f0G48k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93e3661ba24da0a18ce080de09b8bc59d856aab4875021be51f50bbc33a0562
3
+ size 171331342