Add MMS TTS catalan model
Browse files- models/mms/G_100000.pth +3 -0
- models/mms/config.json +87 -0
- models/mms/vocab.txt +39 -0
models/mms/G_100000.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0382edd70333f8ddc663177e672c8a66312e1b30f7929a8f9d458ef66f6b5349
|
3 |
+
size 436622793
|
models/mms/config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"eval_interval": 1000,
|
5 |
+
"seed": 1234,
|
6 |
+
"epochs": 20000,
|
7 |
+
"learning_rate": 0.0002,
|
8 |
+
"betas": [
|
9 |
+
0.8,
|
10 |
+
0.99
|
11 |
+
],
|
12 |
+
"eps": 1e-09,
|
13 |
+
"batch_size": 64,
|
14 |
+
"fp16_run": true,
|
15 |
+
"lr_decay": 0.999875,
|
16 |
+
"segment_size": 8192,
|
17 |
+
"init_lr_ratio": 1,
|
18 |
+
"warmup_epochs": 0,
|
19 |
+
"c_mel": 45,
|
20 |
+
"c_kl": 1.0
|
21 |
+
},
|
22 |
+
"data": {
|
23 |
+
"training_files": "train.ltr",
|
24 |
+
"validation_files": "dev.ltr",
|
25 |
+
"text_cleaners": [
|
26 |
+
"transliteration_cleaners"
|
27 |
+
],
|
28 |
+
"max_wav_value": 32768.0,
|
29 |
+
"sampling_rate": 16000,
|
30 |
+
"filter_length": 1024,
|
31 |
+
"hop_length": 256,
|
32 |
+
"win_length": 1024,
|
33 |
+
"n_mel_channels": 80,
|
34 |
+
"mel_fmin": 0.0,
|
35 |
+
"mel_fmax": null,
|
36 |
+
"add_blank": true,
|
37 |
+
"n_speakers": 0,
|
38 |
+
"cleaned_text": true
|
39 |
+
},
|
40 |
+
"model": {
|
41 |
+
"inter_channels": 192,
|
42 |
+
"hidden_channels": 192,
|
43 |
+
"filter_channels": 768,
|
44 |
+
"n_heads": 2,
|
45 |
+
"n_layers": 6,
|
46 |
+
"kernel_size": 3,
|
47 |
+
"p_dropout": 0.1,
|
48 |
+
"resblock": "1",
|
49 |
+
"resblock_kernel_sizes": [
|
50 |
+
3,
|
51 |
+
7,
|
52 |
+
11
|
53 |
+
],
|
54 |
+
"resblock_dilation_sizes": [
|
55 |
+
[
|
56 |
+
1,
|
57 |
+
3,
|
58 |
+
5
|
59 |
+
],
|
60 |
+
[
|
61 |
+
1,
|
62 |
+
3,
|
63 |
+
5
|
64 |
+
],
|
65 |
+
[
|
66 |
+
1,
|
67 |
+
3,
|
68 |
+
5
|
69 |
+
]
|
70 |
+
],
|
71 |
+
"upsample_rates": [
|
72 |
+
8,
|
73 |
+
8,
|
74 |
+
2,
|
75 |
+
2
|
76 |
+
],
|
77 |
+
"upsample_initial_channel": 512,
|
78 |
+
"upsample_kernel_sizes": [
|
79 |
+
16,
|
80 |
+
16,
|
81 |
+
4,
|
82 |
+
4
|
83 |
+
],
|
84 |
+
"n_layers_q": 3,
|
85 |
+
"use_spectral_norm": false
|
86 |
+
}
|
87 |
+
}
|
models/mms/vocab.txt
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
z
|
2 |
+
f
|
3 |
+
i
|
4 |
+
g
|
5 |
+
m
|
6 |
+
o
|
7 |
+
r
|
8 |
+
è
|
9 |
+
h
|
10 |
+
l
|
11 |
+
v
|
12 |
+
à
|
13 |
+
u
|
14 |
+
d
|
15 |
+
ú
|
16 |
+
ç
|
17 |
+
p
|
18 |
+
s
|
19 |
+
'
|
20 |
+
é
|
21 |
+
_
|
22 |
+
-
|
23 |
+
e
|
24 |
+
a
|
25 |
+
—
|
26 |
+
x
|
27 |
+
ü
|
28 |
+
q
|
29 |
+
t
|
30 |
+
b
|
31 |
+
í
|
32 |
+
ó
|
33 |
+
ï
|
34 |
+
ò
|
35 |
+
|
36 |
+
c
|
37 |
+
j
|
38 |
+
n
|
39 |
+
y
|