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 Community
PluginsKers commited on
Commit
e13eb02
·
verified ·
1 Parent(s): 5d5aaf8

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. chinese-hubert-base/hifigan-nsf/config.json +46 -0
  2. contentvec/sifigan/config.json +46 -0
  3. spin/hifigan-nsf/config.json +46 -0
  4. spin/sifigan/config.json +46 -0
chinese-hubert-base/hifigan-nsf/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/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-nsf/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/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
+ }