Hugging Face's logo

Voicemod
/
fastspeech2-mf-ms

Model card Files Community
arampacha commited on
Commit
6ba830a
•
1 Parent(s): 3b542dd

model

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. .ipynb_checkpoints/config-checkpoint.yaml +34 -0
  3. config.yaml +34 -0
  4. gcmvn_stats.npz +3 -0
  5. hifigan.bin +3 -0
  6. hifigan.json +37 -0
  7. pytorch_model.pt +3 -0
  8. speakers.txt +1 -0
  9. vocab.txt +71 -0
  10. vocab1.txt +66 -0
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ gcmvn_stats.npz filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/config-checkpoint.yaml ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ audio_root: ./morgan_freeman/feature_manifest/
2
+ features:
3
+ energy_max: 4.516870975494385
4
+ energy_min: 0.0
5
+ eps: 1.0e-05
6
+ f_max: 8000
7
+ f_min: 0
8
+ hop_len_t: 0.011609977324263039
9
+ hop_length: 256
10
+ n_fft: 1024
11
+ n_mels: 80
12
+ n_stft: 513
13
+ pitch_max: 6.403360928786941
14
+ pitch_min: 1.0e-08
15
+ sample_rate: 22050
16
+ type: spectrogram+melscale+log
17
+ win_len_t: 0.046439909297052155
18
+ win_length: 1024
19
+ window_fn: hann
20
+ global_cmvn:
21
+ stats_npz_path: morgan_freeman/feature_manifest/gcmvn_stats.npz
22
+ sample_rate: 22050
23
+ transforms:
24
+ '*':
25
+ - global_cmvn
26
+ vocab_filename: vocab.txt
27
+ speaker_set_filename: speakers.txt
28
+ vocoder:
29
+ type: hifigan
30
+ config: hifigan.json
31
+ checkpoint: hifigan.bin
32
+ hub:
33
+ phonemizer: g2p
34
+
config.yaml ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ audio_root: ./morgan_freeman/feature_manifest/
2
+ features:
3
+ energy_max: 4.516870975494385
4
+ energy_min: 0.0
5
+ eps: 1.0e-05
6
+ f_max: 8000
7
+ f_min: 0
8
+ hop_len_t: 0.011609977324263039
9
+ hop_length: 256
10
+ n_fft: 1024
11
+ n_mels: 80
12
+ n_stft: 513
13
+ pitch_max: 6.403360928786941
14
+ pitch_min: 1.0e-08
15
+ sample_rate: 22050
16
+ type: spectrogram+melscale+log
17
+ win_len_t: 0.046439909297052155
18
+ win_length: 1024
19
+ window_fn: hann
20
+ global_cmvn:
21
+ stats_npz_path: morgan_freeman/feature_manifest/gcmvn_stats.npz
22
+ sample_rate: 22050
23
+ transforms:
24
+ '*':
25
+ - global_cmvn
26
+ vocab_filename: vocab.txt
27
+ speaker_set_filename: speakers.txt
28
+ vocoder:
29
+ type: hifigan
30
+ config: hifigan.json
31
+ checkpoint: hifigan.bin
32
+ hub:
33
+ phonemizer: g2p
34
+
gcmvn_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2f9edbdb9d8df51129daef689c8779ddd8bdfd9eb93765773d571d52674d73
3
+ size 1140
hifigan.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce4ab4c65a00d12ea3362375c1eb92f1c54054ac5373801a0dbed9f859102fc3
3
+ size 55825897
hifigan.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "resblock": "1",
3
+ "num_gpus": 0,
4
+ "batch_size": 16,
5
+ "learning_rate": 0.0002,
6
+ "adam_b1": 0.8,
7
+ "adam_b2": 0.99,
8
+ "lr_decay": 0.999,
9
+ "seed": 1234,
10
+
11
+ "upsample_rates": [8,8,2,2],
12
+ "upsample_kernel_sizes": [16,16,4,4],
13
+ "upsample_initial_channel": 512,
14
+ "resblock_kernel_sizes": [3,7,11],
15
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
16
+
17
+ "segment_size": 8192,
18
+ "num_mels": 80,
19
+ "num_freq": 1025,
20
+ "n_fft": 1024,
21
+ "hop_size": 256,
22
+ "win_size": 1024,
23
+
24
+ "sampling_rate": 22050,
25
+
26
+ "fmin": 0,
27
+ "fmax": 8000,
28
+ "fmax_for_loss": null,
29
+
30
+ "num_workers": 4,
31
+
32
+ "dist_config": {
33
+ "dist_backend": "nccl",
34
+ "dist_url": "tcp://localhost:54321",
35
+ "world_size": 1
36
+ }
37
+ }
pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce0664bec9574e3d97369718f8f51f1fa7fba36c73c15754d6d1f0086a56487
3
+ size 387576957
speakers.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ morgan_freeman
vocab.txt ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ AH0 71007
2
+ N 63410
3
+ T 60842
4
+ S 40263
5
+ D 39886
6
+ R 35965
7
+ L 30358
8
+ sp 27584
9
+ IH0 27113
10
+ DH 26584
11
+ K 25851
12
+ IH1 25683
13
+ Z 25387
14
+ EH1 21690
15
+ AE1 21648
16
+ M 21537
17
+ W 18760
18
+ P 18458
19
+ ER0 18446
20
+ V 18169
21
+ IY0 17832
22
+ AH1 16995
23
+ F 15549
24
+ B 14227
25
+ HH 13468
26
+ IY1 12751
27
+ EY1 12141
28
+ AO1 11595
29
+ AA1 10589
30
+ AY1 9624
31
+ UW1 8865
32
+ SH 7449
33
+ OW1 7441
34
+ NG 6705
35
+ G 5472
36
+ ER1 4898
37
+ Y 4548
38
+ JH 4486
39
+ CH 4355
40
+ TH 3980
41
+ AW1 3607
42
+ UH1 2469
43
+ EH2 1881
44
+ spn 1774
45
+ AO0 1357
46
+ OW0 1328
47
+ EY2 1258
48
+ IH2 1251
49
+ AE2 1104
50
+ UW0 1077
51
+ AY2 1062
52
+ AA2 774
53
+ OY1 771
54
+ AO2 622
55
+ ZH 587
56
+ EH0 568
57
+ OW2 557
58
+ EY0 443
59
+ IY2 435
60
+ UW2 431
61
+ AY0 390
62
+ AE0 374
63
+ AH2 316
64
+ AW2 290
65
+ AA0 259
66
+ ER2 136
67
+ UH2 127
68
+ OY2 44
69
+ UH0 36
70
+ AW0 35
71
+ OY0 4
vocab1.txt ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ T 4931
2
+ N 3744
3
+ AH0 3509
4
+ R 2837
5
+ S 2833
6
+ L 2417
7
+ D 2362
8
+ M 2027
9
+ IH1 1850
10
+ IH0 1780
11
+ DH 1772
12
+ AY1 1730
13
+ K 1714
14
+ UW1 1588
15
+ EH1 1568
16
+ AH1 1550
17
+ W 1485
18
+ Z 1465
19
+ Y 1429
20
+ AE1 1377
21
+ IY1 1370
22
+ HH 1355
23
+ ER0 1262
24
+ F 1231
25
+ B 1180
26
+ V 1062
27
+ AO1 1060
28
+ P 986
29
+ EY1 975
30
+ IY0 941
31
+ AA1 939
32
+ OW1 819
33
+ G 798
34
+ NG 701
35
+ AW1 468
36
+ UH1 388
37
+ JH 356
38
+ SH 339
39
+ TH 324
40
+ ER1 317
41
+ spn 250
42
+ CH 230
43
+ AH2 81
44
+ OW0 71
45
+ EH2 58
46
+ IH2 58
47
+ OW2 55
48
+ OY1 45
49
+ AY2 43
50
+ EH0 42
51
+ EY2 35
52
+ UW0 30
53
+ AE2 28
54
+ AA2 24
55
+ AO2 23
56
+ AW2 20
57
+ AO0 17
58
+ IY2 15
59
+ AE0 14
60
+ AA0 12
61
+ UW2 7
62
+ OY0 4
63
+ AW0 4
64
+ UH2 4
65
+ UH0 4
66
+ AY0 4