Commit
•
17530a7
1
Parent(s):
d197f02
move all
Browse files- README.md +12 -0
- config.yaml +24 -0
- fbank_mfa_gcmvn_stats.npz +0 -0
- pytorch_model.pt +3 -0
- run_fast_speech_2.py +5 -0
- vocab.txt +71 -0
README.md
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## Example to download fastspeech2 from fairseq
|
2 |
+
|
3 |
+
Weights are downloaded from:
|
4 |
+
|
5 |
+
We still need to git clone this repo first before being able to download it.
|
6 |
+
Having `cd`'ed into the repo we can do the following:
|
7 |
+
|
8 |
+
```python
|
9 |
+
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf
|
10 |
+
|
11 |
+
model = load_model_ensemble_and_task_from_hf("patrickvonplaten/fairseq-fastspeech2")
|
12 |
+
```
|
config.yaml
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
features:
|
2 |
+
energy_max: 3.2244551181793213
|
3 |
+
energy_min: -4.9544901847839355
|
4 |
+
eps: 1.0e-05
|
5 |
+
f_max: 8000
|
6 |
+
f_min: 0
|
7 |
+
hop_len_t: 0.011609977324263039
|
8 |
+
hop_length: 256
|
9 |
+
n_fft: 1024
|
10 |
+
n_mels: 80
|
11 |
+
n_stft: 513
|
12 |
+
pitch_max: 5.733940816898645
|
13 |
+
pitch_min: -4.660287183665281
|
14 |
+
sample_rate: 22050
|
15 |
+
type: spectrogram+melscale+log
|
16 |
+
win_len_t: 0.046439909297052155
|
17 |
+
win_length: 1024
|
18 |
+
window_fn: hann
|
19 |
+
global_cmvn:
|
20 |
+
stats_npz_path: fbank_mfa_gcmvn_stats.npz
|
21 |
+
transforms:
|
22 |
+
'*':
|
23 |
+
- global_cmvn
|
24 |
+
vocab_filename: vocab.txt
|
fbank_mfa_gcmvn_stats.npz
ADDED
Binary file (1.14 kB). View file
|
|
pytorch_model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a48d454fe66939079d0ddb70f1c062ec669f521a7cfadc608968746e312986ab
|
3 |
+
size 494816801
|
run_fast_speech_2.py
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python3
|
2 |
+
from fairseq.checkpoint_utils import load_model_ensemble_and_task
|
3 |
+
|
4 |
+
# model = load_model_ensemble_and_task(["./pytorch_model.pt"], arg_overrides={"config_yaml": "./config.yaml", "data": "./"})
|
5 |
+
model = load_model_ensemble_and_task(["./pytorch_model.pt"], arg_overrides={"data": "./"})
|
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
|