add files
Browse files- README.md +22 -0
- dump/xvector/dev-clean_phn/spk_xvector.ark +3 -0
- dump/xvector/dev-clean_phn/spk_xvector.scp +96 -0
- dump/xvector/test-clean_phn/spk_xvector.ark +3 -0
- dump/xvector/test-clean_phn/spk_xvector.scp +81 -0
- dump/xvector/train-clean-460_phn/spk_xvector.ark +3 -0
- dump/xvector/train-clean-460_phn/spk_xvector.scp +0 -0
- exp/tts_prodiff_gst_xvector_raw_phn_none/config.yaml +292 -0
- exp/tts_prodiff_gst_xvector_raw_phn_none/train.loss.ave_5best.pth +3 -0
- exp/tts_stats_raw_phn_none/train/energy_stats.npz +3 -0
- exp/tts_stats_raw_phn_none/train/feats_stats.npz +3 -0
- exp/tts_stats_raw_phn_none/train/pitch_stats.npz +3 -0
- meta.yaml +8 -0
README.md
CHANGED
@@ -1,3 +1,25 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: cc-by-4.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- espnet
|
4 |
+
- audio
|
5 |
+
- text-to-speech
|
6 |
+
language:
|
7 |
+
- en
|
8 |
+
datasets:
|
9 |
+
- libritts
|
10 |
license: cc-by-4.0
|
11 |
---
|
12 |
+
|
13 |
+
## TTS model - ProDiff with GST + X-Vector
|
14 |
+
|
15 |
+
**No support given.**
|
16 |
+
|
17 |
+
### Details
|
18 |
+
|
19 |
+
```
|
20 |
+
num_iters_per_epoch: 250
|
21 |
+
max_epoch: 800
|
22 |
+
batch_bins: 8000000
|
23 |
+
tts_conf:
|
24 |
+
spk_embed_dim: 192
|
25 |
+
```
|
dump/xvector/dev-clean_phn/spk_xvector.ark
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d722f8ab5a511b81e45c36a6d87bfdcd7224ceb6539799c8b74f9ab5c8f6cadc
|
3 |
+
size 76265
|
dump/xvector/dev-clean_phn/spk_xvector.scp
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
1272_128104 dump/xvector/dev-clean_phn/spk_xvector.ark:12
|
2 |
+
1272_135031 dump/xvector/dev-clean_phn/spk_xvector.ark:807
|
3 |
+
1272_141231 dump/xvector/dev-clean_phn/spk_xvector.ark:1602
|
4 |
+
1462_170138 dump/xvector/dev-clean_phn/spk_xvector.ark:2397
|
5 |
+
1462_170142 dump/xvector/dev-clean_phn/spk_xvector.ark:3192
|
6 |
+
1462_170145 dump/xvector/dev-clean_phn/spk_xvector.ark:3987
|
7 |
+
1673_143396 dump/xvector/dev-clean_phn/spk_xvector.ark:4782
|
8 |
+
1673_143397 dump/xvector/dev-clean_phn/spk_xvector.ark:5577
|
9 |
+
174_168635 dump/xvector/dev-clean_phn/spk_xvector.ark:6371
|
10 |
+
174_50561 dump/xvector/dev-clean_phn/spk_xvector.ark:7164
|
11 |
+
174_84280 dump/xvector/dev-clean_phn/spk_xvector.ark:7957
|
12 |
+
1919_142785 dump/xvector/dev-clean_phn/spk_xvector.ark:8752
|
13 |
+
1988_147956 dump/xvector/dev-clean_phn/spk_xvector.ark:9547
|
14 |
+
1988_148538 dump/xvector/dev-clean_phn/spk_xvector.ark:10342
|
15 |
+
1988_24833 dump/xvector/dev-clean_phn/spk_xvector.ark:11136
|
16 |
+
1993_147149 dump/xvector/dev-clean_phn/spk_xvector.ark:11931
|
17 |
+
1993_147964 dump/xvector/dev-clean_phn/spk_xvector.ark:12726
|
18 |
+
1993_147965 dump/xvector/dev-clean_phn/spk_xvector.ark:13521
|
19 |
+
1993_147966 dump/xvector/dev-clean_phn/spk_xvector.ark:14316
|
20 |
+
2035_147960 dump/xvector/dev-clean_phn/spk_xvector.ark:15111
|
21 |
+
2035_147961 dump/xvector/dev-clean_phn/spk_xvector.ark:15906
|
22 |
+
2035_152373 dump/xvector/dev-clean_phn/spk_xvector.ark:16701
|
23 |
+
2078_142845 dump/xvector/dev-clean_phn/spk_xvector.ark:17496
|
24 |
+
2086_149214 dump/xvector/dev-clean_phn/spk_xvector.ark:18291
|
25 |
+
2086_149220 dump/xvector/dev-clean_phn/spk_xvector.ark:19086
|
26 |
+
2277_149874 dump/xvector/dev-clean_phn/spk_xvector.ark:19881
|
27 |
+
2277_149896 dump/xvector/dev-clean_phn/spk_xvector.ark:20676
|
28 |
+
2277_149897 dump/xvector/dev-clean_phn/spk_xvector.ark:21471
|
29 |
+
2412_153947 dump/xvector/dev-clean_phn/spk_xvector.ark:22266
|
30 |
+
2412_153948 dump/xvector/dev-clean_phn/spk_xvector.ark:23061
|
31 |
+
2412_153954 dump/xvector/dev-clean_phn/spk_xvector.ark:23856
|
32 |
+
2428_83699 dump/xvector/dev-clean_phn/spk_xvector.ark:24650
|
33 |
+
2428_83705 dump/xvector/dev-clean_phn/spk_xvector.ark:25444
|
34 |
+
251_118436 dump/xvector/dev-clean_phn/spk_xvector.ark:26238
|
35 |
+
251_136532 dump/xvector/dev-clean_phn/spk_xvector.ark:27032
|
36 |
+
251_137823 dump/xvector/dev-clean_phn/spk_xvector.ark:27826
|
37 |
+
2803_154320 dump/xvector/dev-clean_phn/spk_xvector.ark:28621
|
38 |
+
2803_154328 dump/xvector/dev-clean_phn/spk_xvector.ark:29416
|
39 |
+
2803_161169 dump/xvector/dev-clean_phn/spk_xvector.ark:30211
|
40 |
+
2902_9006 dump/xvector/dev-clean_phn/spk_xvector.ark:31004
|
41 |
+
2902_9008 dump/xvector/dev-clean_phn/spk_xvector.ark:31797
|
42 |
+
3000_15664 dump/xvector/dev-clean_phn/spk_xvector.ark:32591
|
43 |
+
3081_166546 dump/xvector/dev-clean_phn/spk_xvector.ark:33386
|
44 |
+
3170_137482 dump/xvector/dev-clean_phn/spk_xvector.ark:34181
|
45 |
+
3536_23268 dump/xvector/dev-clean_phn/spk_xvector.ark:34975
|
46 |
+
3536_8226 dump/xvector/dev-clean_phn/spk_xvector.ark:35768
|
47 |
+
3576_138058 dump/xvector/dev-clean_phn/spk_xvector.ark:36563
|
48 |
+
3752_4943 dump/xvector/dev-clean_phn/spk_xvector.ark:37356
|
49 |
+
3752_4944 dump/xvector/dev-clean_phn/spk_xvector.ark:38149
|
50 |
+
3853_163249 dump/xvector/dev-clean_phn/spk_xvector.ark:38944
|
51 |
+
422_122949 dump/xvector/dev-clean_phn/spk_xvector.ark:39738
|
52 |
+
5338_24615 dump/xvector/dev-clean_phn/spk_xvector.ark:40532
|
53 |
+
5338_24640 dump/xvector/dev-clean_phn/spk_xvector.ark:41326
|
54 |
+
5338_284437 dump/xvector/dev-clean_phn/spk_xvector.ark:42121
|
55 |
+
5536_43358 dump/xvector/dev-clean_phn/spk_xvector.ark:42915
|
56 |
+
5536_43359 dump/xvector/dev-clean_phn/spk_xvector.ark:43709
|
57 |
+
5536_43363 dump/xvector/dev-clean_phn/spk_xvector.ark:44503
|
58 |
+
5694_64025 dump/xvector/dev-clean_phn/spk_xvector.ark:45297
|
59 |
+
5694_64029 dump/xvector/dev-clean_phn/spk_xvector.ark:46091
|
60 |
+
5694_64038 dump/xvector/dev-clean_phn/spk_xvector.ark:46885
|
61 |
+
5895_34615 dump/xvector/dev-clean_phn/spk_xvector.ark:47679
|
62 |
+
5895_34622 dump/xvector/dev-clean_phn/spk_xvector.ark:48473
|
63 |
+
5895_34629 dump/xvector/dev-clean_phn/spk_xvector.ark:49267
|
64 |
+
6241_61943 dump/xvector/dev-clean_phn/spk_xvector.ark:50061
|
65 |
+
6241_61946 dump/xvector/dev-clean_phn/spk_xvector.ark:50855
|
66 |
+
6241_66616 dump/xvector/dev-clean_phn/spk_xvector.ark:51649
|
67 |
+
6295_244435 dump/xvector/dev-clean_phn/spk_xvector.ark:52444
|
68 |
+
6295_64301 dump/xvector/dev-clean_phn/spk_xvector.ark:53238
|
69 |
+
6313_66125 dump/xvector/dev-clean_phn/spk_xvector.ark:54032
|
70 |
+
6313_66129 dump/xvector/dev-clean_phn/spk_xvector.ark:54826
|
71 |
+
6313_76958 dump/xvector/dev-clean_phn/spk_xvector.ark:55620
|
72 |
+
6319_275224 dump/xvector/dev-clean_phn/spk_xvector.ark:56415
|
73 |
+
6319_57405 dump/xvector/dev-clean_phn/spk_xvector.ark:57209
|
74 |
+
6319_64726 dump/xvector/dev-clean_phn/spk_xvector.ark:58003
|
75 |
+
6345_64257 dump/xvector/dev-clean_phn/spk_xvector.ark:58797
|
76 |
+
6345_93302 dump/xvector/dev-clean_phn/spk_xvector.ark:59591
|
77 |
+
6345_93306 dump/xvector/dev-clean_phn/spk_xvector.ark:60385
|
78 |
+
652_129742 dump/xvector/dev-clean_phn/spk_xvector.ark:61179
|
79 |
+
652_130737 dump/xvector/dev-clean_phn/spk_xvector.ark:61973
|
80 |
+
777_126732 dump/xvector/dev-clean_phn/spk_xvector.ark:62767
|
81 |
+
7850_111771 dump/xvector/dev-clean_phn/spk_xvector.ark:63562
|
82 |
+
7850_281318 dump/xvector/dev-clean_phn/spk_xvector.ark:64357
|
83 |
+
7850_286674 dump/xvector/dev-clean_phn/spk_xvector.ark:65152
|
84 |
+
7850_73752 dump/xvector/dev-clean_phn/spk_xvector.ark:65946
|
85 |
+
7976_105575 dump/xvector/dev-clean_phn/spk_xvector.ark:66741
|
86 |
+
7976_110124 dump/xvector/dev-clean_phn/spk_xvector.ark:67536
|
87 |
+
7976_110523 dump/xvector/dev-clean_phn/spk_xvector.ark:68331
|
88 |
+
8297_275154 dump/xvector/dev-clean_phn/spk_xvector.ark:69126
|
89 |
+
8297_275155 dump/xvector/dev-clean_phn/spk_xvector.ark:69921
|
90 |
+
8297_275156 dump/xvector/dev-clean_phn/spk_xvector.ark:70716
|
91 |
+
84_121123 dump/xvector/dev-clean_phn/spk_xvector.ark:71509
|
92 |
+
84_121550 dump/xvector/dev-clean_phn/spk_xvector.ark:72302
|
93 |
+
8842_302196 dump/xvector/dev-clean_phn/spk_xvector.ark:73097
|
94 |
+
8842_302201 dump/xvector/dev-clean_phn/spk_xvector.ark:73892
|
95 |
+
8842_302203 dump/xvector/dev-clean_phn/spk_xvector.ark:74687
|
96 |
+
8842_304647 dump/xvector/dev-clean_phn/spk_xvector.ark:75482
|
dump/xvector/test-clean_phn/spk_xvector.ark
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16195491f8b865a1c6efa87133219fe8cf8a07b4a877b5dbb9043e5ebcdfe104
|
3 |
+
size 64316
|
dump/xvector/test-clean_phn/spk_xvector.scp
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
1089_134686 dump/xvector/test-clean_phn/spk_xvector.ark:12
|
2 |
+
1089_134691 dump/xvector/test-clean_phn/spk_xvector.ark:807
|
3 |
+
1188_133604 dump/xvector/test-clean_phn/spk_xvector.ark:1602
|
4 |
+
121_121726 dump/xvector/test-clean_phn/spk_xvector.ark:2396
|
5 |
+
121_123859 dump/xvector/test-clean_phn/spk_xvector.ark:3190
|
6 |
+
121_127105 dump/xvector/test-clean_phn/spk_xvector.ark:3984
|
7 |
+
1221_135766 dump/xvector/test-clean_phn/spk_xvector.ark:4779
|
8 |
+
1221_135767 dump/xvector/test-clean_phn/spk_xvector.ark:5574
|
9 |
+
1284_1180 dump/xvector/test-clean_phn/spk_xvector.ark:6367
|
10 |
+
1284_1181 dump/xvector/test-clean_phn/spk_xvector.ark:7160
|
11 |
+
1320_122612 dump/xvector/test-clean_phn/spk_xvector.ark:7955
|
12 |
+
1320_122617 dump/xvector/test-clean_phn/spk_xvector.ark:8750
|
13 |
+
1580_141083 dump/xvector/test-clean_phn/spk_xvector.ark:9545
|
14 |
+
1580_141084 dump/xvector/test-clean_phn/spk_xvector.ark:10340
|
15 |
+
1995_1826 dump/xvector/test-clean_phn/spk_xvector.ark:11133
|
16 |
+
1995_1836 dump/xvector/test-clean_phn/spk_xvector.ark:11926
|
17 |
+
1995_1837 dump/xvector/test-clean_phn/spk_xvector.ark:12719
|
18 |
+
2300_131720 dump/xvector/test-clean_phn/spk_xvector.ark:13514
|
19 |
+
237_126133 dump/xvector/test-clean_phn/spk_xvector.ark:14308
|
20 |
+
237_134493 dump/xvector/test-clean_phn/spk_xvector.ark:15102
|
21 |
+
237_134500 dump/xvector/test-clean_phn/spk_xvector.ark:15896
|
22 |
+
260_123286 dump/xvector/test-clean_phn/spk_xvector.ark:16690
|
23 |
+
260_123288 dump/xvector/test-clean_phn/spk_xvector.ark:17484
|
24 |
+
260_123440 dump/xvector/test-clean_phn/spk_xvector.ark:18278
|
25 |
+
2830_3979 dump/xvector/test-clean_phn/spk_xvector.ark:19071
|
26 |
+
2830_3980 dump/xvector/test-clean_phn/spk_xvector.ark:19864
|
27 |
+
2961_961 dump/xvector/test-clean_phn/spk_xvector.ark:20656
|
28 |
+
3570_5694 dump/xvector/test-clean_phn/spk_xvector.ark:21449
|
29 |
+
3570_5695 dump/xvector/test-clean_phn/spk_xvector.ark:22242
|
30 |
+
3570_5696 dump/xvector/test-clean_phn/spk_xvector.ark:23035
|
31 |
+
3575_170457 dump/xvector/test-clean_phn/spk_xvector.ark:23830
|
32 |
+
3729_6852 dump/xvector/test-clean_phn/spk_xvector.ark:24623
|
33 |
+
4077_13751 dump/xvector/test-clean_phn/spk_xvector.ark:25417
|
34 |
+
4077_13754 dump/xvector/test-clean_phn/spk_xvector.ark:26211
|
35 |
+
4446_2271 dump/xvector/test-clean_phn/spk_xvector.ark:27004
|
36 |
+
4446_2273 dump/xvector/test-clean_phn/spk_xvector.ark:27797
|
37 |
+
4446_2275 dump/xvector/test-clean_phn/spk_xvector.ark:28590
|
38 |
+
4507_16021 dump/xvector/test-clean_phn/spk_xvector.ark:29384
|
39 |
+
4970_29093 dump/xvector/test-clean_phn/spk_xvector.ark:30178
|
40 |
+
4970_29095 dump/xvector/test-clean_phn/spk_xvector.ark:30972
|
41 |
+
4992_23283 dump/xvector/test-clean_phn/spk_xvector.ark:31766
|
42 |
+
4992_41797 dump/xvector/test-clean_phn/spk_xvector.ark:32560
|
43 |
+
4992_41806 dump/xvector/test-clean_phn/spk_xvector.ark:33354
|
44 |
+
5105_28233 dump/xvector/test-clean_phn/spk_xvector.ark:34148
|
45 |
+
5105_28240 dump/xvector/test-clean_phn/spk_xvector.ark:34942
|
46 |
+
5105_28241 dump/xvector/test-clean_phn/spk_xvector.ark:35736
|
47 |
+
5142_33396 dump/xvector/test-clean_phn/spk_xvector.ark:36530
|
48 |
+
5142_36377 dump/xvector/test-clean_phn/spk_xvector.ark:37324
|
49 |
+
5142_36586 dump/xvector/test-clean_phn/spk_xvector.ark:38118
|
50 |
+
5142_36600 dump/xvector/test-clean_phn/spk_xvector.ark:38912
|
51 |
+
5639_40744 dump/xvector/test-clean_phn/spk_xvector.ark:39706
|
52 |
+
5683_32865 dump/xvector/test-clean_phn/spk_xvector.ark:40500
|
53 |
+
5683_32866 dump/xvector/test-clean_phn/spk_xvector.ark:41294
|
54 |
+
5683_32879 dump/xvector/test-clean_phn/spk_xvector.ark:42088
|
55 |
+
61_70970 dump/xvector/test-clean_phn/spk_xvector.ark:42880
|
56 |
+
672_122797 dump/xvector/test-clean_phn/spk_xvector.ark:43674
|
57 |
+
6829_68769 dump/xvector/test-clean_phn/spk_xvector.ark:44468
|
58 |
+
6829_68771 dump/xvector/test-clean_phn/spk_xvector.ark:45262
|
59 |
+
6930_75918 dump/xvector/test-clean_phn/spk_xvector.ark:46056
|
60 |
+
6930_76324 dump/xvector/test-clean_phn/spk_xvector.ark:46850
|
61 |
+
6930_81414 dump/xvector/test-clean_phn/spk_xvector.ark:47644
|
62 |
+
7021_79730 dump/xvector/test-clean_phn/spk_xvector.ark:48438
|
63 |
+
7021_79740 dump/xvector/test-clean_phn/spk_xvector.ark:49232
|
64 |
+
7021_79759 dump/xvector/test-clean_phn/spk_xvector.ark:50026
|
65 |
+
7021_85628 dump/xvector/test-clean_phn/spk_xvector.ark:50820
|
66 |
+
7127_75946 dump/xvector/test-clean_phn/spk_xvector.ark:51614
|
67 |
+
7127_75947 dump/xvector/test-clean_phn/spk_xvector.ark:52408
|
68 |
+
7176_88083 dump/xvector/test-clean_phn/spk_xvector.ark:53202
|
69 |
+
7176_92135 dump/xvector/test-clean_phn/spk_xvector.ark:53996
|
70 |
+
7729_102255 dump/xvector/test-clean_phn/spk_xvector.ark:54791
|
71 |
+
8224_274384 dump/xvector/test-clean_phn/spk_xvector.ark:55586
|
72 |
+
8230_279154 dump/xvector/test-clean_phn/spk_xvector.ark:56381
|
73 |
+
8455_210777 dump/xvector/test-clean_phn/spk_xvector.ark:57176
|
74 |
+
8463_287645 dump/xvector/test-clean_phn/spk_xvector.ark:57971
|
75 |
+
8463_294825 dump/xvector/test-clean_phn/spk_xvector.ark:58766
|
76 |
+
8463_294828 dump/xvector/test-clean_phn/spk_xvector.ark:59561
|
77 |
+
8555_284447 dump/xvector/test-clean_phn/spk_xvector.ark:60356
|
78 |
+
8555_284449 dump/xvector/test-clean_phn/spk_xvector.ark:61151
|
79 |
+
8555_292519 dump/xvector/test-clean_phn/spk_xvector.ark:61946
|
80 |
+
908_157963 dump/xvector/test-clean_phn/spk_xvector.ark:62740
|
81 |
+
908_31957 dump/xvector/test-clean_phn/spk_xvector.ark:63533
|
dump/xvector/train-clean-460_phn/spk_xvector.ark
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b140d860c5014234c0233e6eacd6b2df1175f1ae6318a2f8bc94f258aff5fcc1
|
3 |
+
size 2032667
|
dump/xvector/train-clean-460_phn/spk_xvector.scp
ADDED
The diff for this file is too large to render.
See raw diff
|
|
exp/tts_prodiff_gst_xvector_raw_phn_none/config.yaml
ADDED
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config: conf/tuning/prodiff_gst_xvector.yaml
|
2 |
+
print_config: false
|
3 |
+
log_level: INFO
|
4 |
+
dry_run: false
|
5 |
+
iterator_type: sequence
|
6 |
+
output_dir: exp/tts_prodiff_gst_xvector_raw_phn_none
|
7 |
+
ngpu: 1
|
8 |
+
seed: 0
|
9 |
+
num_workers: 6
|
10 |
+
num_att_plot: 3
|
11 |
+
num_valid_artifacts: 5
|
12 |
+
dist_backend: nccl
|
13 |
+
dist_init_method: env://
|
14 |
+
dist_world_size: null
|
15 |
+
dist_rank: null
|
16 |
+
local_rank: 0
|
17 |
+
dist_master_addr: null
|
18 |
+
dist_master_port: null
|
19 |
+
dist_launcher: null
|
20 |
+
multiprocessing_distributed: false
|
21 |
+
unused_parameters: false
|
22 |
+
sharded_ddp: false
|
23 |
+
growth_interval: 0
|
24 |
+
min_grad_scale: -1
|
25 |
+
cudnn_enabled: true
|
26 |
+
cudnn_benchmark: false
|
27 |
+
cudnn_deterministic: true
|
28 |
+
collect_stats: false
|
29 |
+
write_collected_feats: false
|
30 |
+
max_epoch: 800
|
31 |
+
patience: null
|
32 |
+
val_scheduler_criterion:
|
33 |
+
- valid
|
34 |
+
- loss
|
35 |
+
early_stopping_criterion:
|
36 |
+
- valid
|
37 |
+
- loss
|
38 |
+
- min
|
39 |
+
best_model_criterion:
|
40 |
+
- - valid
|
41 |
+
- loss
|
42 |
+
- min
|
43 |
+
- - train
|
44 |
+
- loss
|
45 |
+
- min
|
46 |
+
keep_nbest_models: 5
|
47 |
+
nbest_averaging_interval: 0
|
48 |
+
grad_clip: 1.0
|
49 |
+
grad_clip_type: 2.0
|
50 |
+
grad_noise: false
|
51 |
+
accum_grad: 1
|
52 |
+
no_forward_run: false
|
53 |
+
resume: true
|
54 |
+
train_dtype: float32
|
55 |
+
use_amp: false
|
56 |
+
log_interval: null
|
57 |
+
use_matplotlib: true
|
58 |
+
use_tensorboard: true
|
59 |
+
detect_anomaly: false
|
60 |
+
pretrain_path: null
|
61 |
+
init_param: []
|
62 |
+
ignore_init_mismatch: false
|
63 |
+
freeze_param: []
|
64 |
+
num_iters_per_epoch: 250
|
65 |
+
batch_size: 20
|
66 |
+
valid_batch_size: null
|
67 |
+
batch_bins: 8000000
|
68 |
+
valid_batch_bins: null
|
69 |
+
train_shape_file:
|
70 |
+
- exp/tts_stats_raw_phn_none/train/text_shape.phn
|
71 |
+
- exp/tts_stats_raw_phn_none/train/speech_shape
|
72 |
+
valid_shape_file:
|
73 |
+
- exp/tts_stats_raw_phn_none/valid/text_shape.phn
|
74 |
+
- exp/tts_stats_raw_phn_none/valid/speech_shape
|
75 |
+
batch_type: numel
|
76 |
+
valid_batch_type: null
|
77 |
+
fold_length:
|
78 |
+
- 150
|
79 |
+
- 240000
|
80 |
+
sort_in_batch: descending
|
81 |
+
sort_batch: descending
|
82 |
+
multiple_iterator: false
|
83 |
+
chunk_length: 500
|
84 |
+
chunk_shift_ratio: 0.5
|
85 |
+
num_cache_chunks: 1024
|
86 |
+
train_data_path_and_name_and_type:
|
87 |
+
- - dump/raw/train-clean-460_phn/text
|
88 |
+
- text
|
89 |
+
- text
|
90 |
+
- - data/train-clean-460_phn/durations
|
91 |
+
- durations
|
92 |
+
- text_int
|
93 |
+
- - dump/raw/train-clean-460_phn/wav.scp
|
94 |
+
- speech
|
95 |
+
- sound
|
96 |
+
- - exp/tts_stats_raw_phn_none/train/collect_feats/pitch.scp
|
97 |
+
- pitch
|
98 |
+
- npy
|
99 |
+
- - exp/tts_stats_raw_phn_none/train/collect_feats/energy.scp
|
100 |
+
- energy
|
101 |
+
- npy
|
102 |
+
- - dump/xvector/train-clean-460_phn/xvector.scp
|
103 |
+
- spembs
|
104 |
+
- kaldi_ark
|
105 |
+
valid_data_path_and_name_and_type:
|
106 |
+
- - dump/raw/dev-clean_phn/text
|
107 |
+
- text
|
108 |
+
- text
|
109 |
+
- - data/dev-clean_phn/durations
|
110 |
+
- durations
|
111 |
+
- text_int
|
112 |
+
- - dump/raw/dev-clean_phn/wav.scp
|
113 |
+
- speech
|
114 |
+
- sound
|
115 |
+
- - exp/tts_stats_raw_phn_none/valid/collect_feats/pitch.scp
|
116 |
+
- pitch
|
117 |
+
- npy
|
118 |
+
- - exp/tts_stats_raw_phn_none/valid/collect_feats/energy.scp
|
119 |
+
- energy
|
120 |
+
- npy
|
121 |
+
- - dump/xvector/dev-clean_phn/xvector.scp
|
122 |
+
- spembs
|
123 |
+
- kaldi_ark
|
124 |
+
allow_variable_data_keys: false
|
125 |
+
max_cache_size: 0.0
|
126 |
+
max_cache_fd: 32
|
127 |
+
valid_max_cache_size: null
|
128 |
+
optim: adamw
|
129 |
+
optim_conf:
|
130 |
+
lr: 1.0
|
131 |
+
betas:
|
132 |
+
- 0.9
|
133 |
+
- 0.98
|
134 |
+
scheduler: noamlr
|
135 |
+
scheduler_conf:
|
136 |
+
model_size: 384
|
137 |
+
warmup_steps: 2000
|
138 |
+
token_list:
|
139 |
+
- <blank>
|
140 |
+
- <unk>
|
141 |
+
- ˈ
|
142 |
+
- ɪ
|
143 |
+
- ː
|
144 |
+
- t
|
145 |
+
- n
|
146 |
+
- d
|
147 |
+
- s
|
148 |
+
- ɹ
|
149 |
+
- ə
|
150 |
+
- l
|
151 |
+
- æ
|
152 |
+
- i
|
153 |
+
- ð
|
154 |
+
- ɛ
|
155 |
+
- ʌ
|
156 |
+
- m
|
157 |
+
- k
|
158 |
+
- z
|
159 |
+
- ʊ
|
160 |
+
- a
|
161 |
+
- w
|
162 |
+
- h
|
163 |
+
- sil
|
164 |
+
- p
|
165 |
+
- v
|
166 |
+
- f
|
167 |
+
- u
|
168 |
+
- ','
|
169 |
+
- b
|
170 |
+
- ˌ
|
171 |
+
- ɚ
|
172 |
+
- o
|
173 |
+
- e
|
174 |
+
- ɑ
|
175 |
+
- .
|
176 |
+
- ʃ
|
177 |
+
- ɔ
|
178 |
+
- ŋ
|
179 |
+
- ɐ
|
180 |
+
- ᵻ
|
181 |
+
- ɡ
|
182 |
+
- ɜ
|
183 |
+
- θ
|
184 |
+
- j
|
185 |
+
- ɾ
|
186 |
+
- ʒ
|
187 |
+
- '?'
|
188 |
+
- '!'
|
189 |
+
- ̩
|
190 |
+
- '"'
|
191 |
+
- ʔ
|
192 |
+
- ''''
|
193 |
+
- r
|
194 |
+
- x
|
195 |
+
- ̃
|
196 |
+
- ç
|
197 |
+
- ʲ
|
198 |
+
- <sos/eos>
|
199 |
+
odim: null
|
200 |
+
model_conf:
|
201 |
+
requires_word_duration: false
|
202 |
+
use_preprocessor: true
|
203 |
+
token_type: phn
|
204 |
+
bpemodel: null
|
205 |
+
non_linguistic_symbols: null
|
206 |
+
cleaner: null
|
207 |
+
g2p: null
|
208 |
+
feats_extract: fbank
|
209 |
+
feats_extract_conf:
|
210 |
+
n_fft: 2048
|
211 |
+
hop_length: 300
|
212 |
+
win_length: 1200
|
213 |
+
fs: 24000
|
214 |
+
fmin: 80
|
215 |
+
fmax: 7600
|
216 |
+
n_mels: 80
|
217 |
+
normalize: global_mvn
|
218 |
+
normalize_conf:
|
219 |
+
stats_file: exp/tts_stats_raw_phn_none/train/feats_stats.npz
|
220 |
+
tts: prodiff
|
221 |
+
tts_conf:
|
222 |
+
adim: 256
|
223 |
+
aheads: 2
|
224 |
+
elayers: 4
|
225 |
+
eunits: 1024
|
226 |
+
positionwise_layer_type: conv1d-linear
|
227 |
+
positionwise_conv_kernel_size: 9
|
228 |
+
duration_predictor_layers: 2
|
229 |
+
duration_predictor_chans: 256
|
230 |
+
duration_predictor_kernel_size: 3
|
231 |
+
use_masking: true
|
232 |
+
use_scaled_pos_enc: true
|
233 |
+
encoder_normalize_before: true
|
234 |
+
reduction_factor: 1
|
235 |
+
init_type: xavier_uniform
|
236 |
+
init_enc_alpha: 1.0
|
237 |
+
transformer_enc_dropout_rate: 0.05
|
238 |
+
transformer_enc_positional_dropout_rate: 0.05
|
239 |
+
transformer_enc_attn_dropout_rate: 0.05
|
240 |
+
pitch_predictor_layers: 2
|
241 |
+
pitch_predictor_chans: 256
|
242 |
+
pitch_predictor_kernel_size: 3
|
243 |
+
pitch_predictor_dropout: 0.5
|
244 |
+
pitch_embed_kernel_size: 1
|
245 |
+
pitch_embed_dropout: 0.0
|
246 |
+
stop_gradient_from_pitch_predictor: true
|
247 |
+
energy_predictor_layers: 2
|
248 |
+
energy_predictor_chans: 256
|
249 |
+
energy_predictor_kernel_size: 3
|
250 |
+
energy_predictor_dropout: 0.5
|
251 |
+
energy_embed_kernel_size: 1
|
252 |
+
energy_embed_dropout: 0.0
|
253 |
+
stop_gradient_from_energy_predictor: false
|
254 |
+
spks: -1
|
255 |
+
spk_embed_dim: 192
|
256 |
+
denoiser_dim: 256
|
257 |
+
denoiser_layers: 20
|
258 |
+
denoiser_channels: 256
|
259 |
+
diffusion_steps: 4
|
260 |
+
diffusion_timescale: 1
|
261 |
+
diffusion_beta: 40.0
|
262 |
+
diffusion_scheduler: vpsde
|
263 |
+
diffusion_cycle_ln: 1
|
264 |
+
use_gst: true
|
265 |
+
gst_heads: 8
|
266 |
+
gst_tokens: 128
|
267 |
+
pitch_extract: dio
|
268 |
+
pitch_extract_conf:
|
269 |
+
fs: 24000
|
270 |
+
n_fft: 2048
|
271 |
+
hop_length: 300
|
272 |
+
f0max: 400
|
273 |
+
f0min: 80
|
274 |
+
reduction_factor: 1
|
275 |
+
pitch_normalize: global_mvn
|
276 |
+
pitch_normalize_conf:
|
277 |
+
stats_file: exp/tts_stats_raw_phn_none/train/pitch_stats.npz
|
278 |
+
energy_extract: energy
|
279 |
+
energy_extract_conf:
|
280 |
+
fs: 24000
|
281 |
+
n_fft: 2048
|
282 |
+
hop_length: 300
|
283 |
+
win_length: 1200
|
284 |
+
reduction_factor: 1
|
285 |
+
energy_normalize: global_mvn
|
286 |
+
energy_normalize_conf:
|
287 |
+
stats_file: exp/tts_stats_raw_phn_none/train/energy_stats.npz
|
288 |
+
required:
|
289 |
+
- output_dir
|
290 |
+
- token_list
|
291 |
+
version: '202207'
|
292 |
+
distributed: false
|
exp/tts_prodiff_gst_xvector_raw_phn_none/train.loss.ave_5best.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:515c13e93c97102ee056ecb876c584b3a25bb19bc819c050f636eb0e82ab5e8e
|
3 |
+
size 114211753
|
exp/tts_stats_raw_phn_none/train/energy_stats.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c77441f19c1089a1f1bdd278c65306f58cb2c3175add2589b960da0770378255
|
3 |
+
size 770
|
exp/tts_stats_raw_phn_none/train/feats_stats.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df1d27e5047a24f16c71120cff991928e2f34de2d8dae65e42ba8ee2e3cf1741
|
3 |
+
size 1402
|
exp/tts_stats_raw_phn_none/train/pitch_stats.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c675d24eb48cba744aaac4f1820104691aab94938b1f41e582221293566496b
|
3 |
+
size 770
|
meta.yaml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
espnet: '202207'
|
2 |
+
files:
|
3 |
+
model_file: exp/tts_prodiff_gst_xvector_raw_phn_none/train.loss.ave_5best.pth
|
4 |
+
python: "3.9.13 (main, Aug 25 2022, 23:26:10) \n[GCC 11.2.0]"
|
5 |
+
timestamp: 1673252764.559993
|
6 |
+
torch: 1.12.1
|
7 |
+
yaml_files:
|
8 |
+
train_config: exp/tts_prodiff_gst_xvector_raw_phn_none/config.yaml
|