Li Fuchen
544594ec54
Merge pull request #63 from iclementine/doc
...
update docstrings for models.wavenet.
2020-12-18 20:57:28 +08:00
iclementine
84ad4c9e65
1. update docstrings for models.wavenet;
...
2. remove unnecessary code;
3. fix typos
2020-12-18 20:55:27 +08:00
lfchener
255ddcfe32
modified docstring of tacotron2
2020-12-18 20:28:21 +08:00
lfchener
63285dc80f
add docstring for normalizer
2020-12-18 19:36:12 +08:00
lfchener
c2bc4b0474
add docstring for phonectic and vocab
2020-12-18 19:31:44 +08:00
lfchener
1af9127ee6
add docstring for LocationSensitiveAttention
2020-12-18 17:31:51 +08:00
Feiyu Chan
dd2c5cc6c6
Merge pull request #59 from iclementine/doc
...
update docstrings
2020-12-18 16:12:56 +08:00
iclementine
310366bb54
1. fix format errors and typos
2020-12-18 16:09:38 +08:00
lfchener
3baffa5f4c
update link in docstring
2020-12-18 15:53:24 +08:00
lfchener
6b8573898a
update docstring of tacotron2
2020-12-18 15:50:05 +08:00
lfchener
ecdeb14a40
add docstring for tacotron2
2020-12-18 15:31:40 +08:00
iclementine
d78a8b4e1e
1. update documentations for paddle.modules;
...
2. update TransformerEncoder and TransformerDecoder's implementation(mask and dropout).
2020-12-18 15:31:13 +08:00
iclementine
49c9cb38be
use numpydoc instead of napoleon
2020-12-18 11:12:22 +08:00
iclementine
bbc50faef2
add generated api_doc
2020-12-18 10:54:50 +08:00
Feiyu Chan
b82217f50f
Merge pull request #55 from lfchener/reborn
...
fix EnglishCharacter frontend and add spectrogram plots
2020-12-17 11:16:12 +08:00
lfchener
6420da6197
fix some bugs
2020-12-17 02:56:45 +00:00
chenfeiyu
bdf60bec39
fix wavenet inference shape
2020-12-16 00:22:43 +08:00
lfchener
a5c81c75d5
fix add_spectrogram_plots
2020-12-15 11:27:11 +00:00
lfchener
c864612dc3
plot spectrogram
2020-12-15 09:07:40 +00:00
lfchener
5b93de8a2e
fix EnglishCharacter frontend, add space in sentence ids
2020-12-14 08:57:08 +00:00
lfchener
3a19150344
move model.eval() to manually
2020-12-12 10:34:48 +00:00
chenfeiyu
796e0b1e1f
1. add interfaces for inference;;
...
2. add a function to recursively remove weight norm;
3. wavenet: fix weight norm dimension: explicitly specify dim=1 instead of -1.
2020-12-12 18:21:20 +08:00
lfchener
026ae1078b
add from_pretrained function for tacotron2 and support synthesize
2020-12-12 08:09:15 +00:00
lfchener
99fdd10b5d
add plot alignment function
2020-12-11 12:04:32 +00:00
Feiyu Chan
4de58f4a99
Merge pull request #48 from iclementine/reborn
...
add set_device at experiment setup
2020-12-11 19:50:27 +08:00
chenfeiyu
a079e767df
add set_device at experiment setup
2020-12-11 19:45:49 +08:00
Feiyu Chan
1d2e93c75f
Merge pull request #45 from lfchener/reborn
...
add TTS model tacotron2
2020-12-11 16:33:22 +08:00
lfchener
a8b10f50fb
fix EnglishCharacter numericalize in phonectic.py
2020-12-11 08:31:34 +00:00
chenfeiyu
cecc8735c4
1. fix ExperimentBase, create ouput folder with parent,
...
2. fix stop condition
2020-12-11 11:58:57 +08:00
lfchener
09f1840082
fix some bugs of tacotron2
2020-12-11 03:56:40 +00:00
lfchener
fb64c79f7a
add normalize function in normalizer.py
2020-12-10 07:05:40 +00:00
lfchener
e30d7ad48f
merge upstream develop
2020-12-10 03:37:56 +00:00
chenfeiyu
a1b827460c
fix typos, move quantize/dequantize to moduels/audio
2020-12-09 21:05:39 +08:00
lfchener
f375792c51
add tacotron2.py and a new frontend for en
2020-12-09 12:42:41 +00:00
lfchener
e29502f634
Merge branch 'reborn' of https://github.com/iclementine/Parakeet into reborn
2020-12-09 09:08:46 +00:00
lfchener
b12eda8423
add network of tacotron2 model
2020-12-09 09:08:17 +00:00
chenfeiyu
29cc759241
add access control by __all__ in modules
2020-12-09 15:58:39 +08:00
chenfeiyu
4893c9c086
add an ExperimentBase class and default config for training
2020-12-08 15:46:41 +08:00
chenfeiyu
37d4475810
add default argument parser
2020-12-08 10:56:47 +08:00
chenfeiyu
62959759f9
add linear in decoder prenet
2020-12-05 22:09:44 +08:00
chenfeiyu
0287f46532
switch back to keras style sample weight
2020-12-05 21:08:10 +08:00
chenfeiyu
d3761683e1
add an adaptive loss to balance stop prediction classes
2020-12-05 14:12:30 +08:00
chenfeiyu
a4a0bd8c98
add last bn for the decoder postnet, switch back to weighted mean
2020-12-05 14:00:08 +08:00
chenfeiyu
c57e8e7350
fix transformer_tts' stop condition
2020-12-04 02:11:02 +08:00
chenfeiyu
e87bfb7d05
hide fastspeech, deepvoice3, clarinet temporarily till they are updated
2020-12-03 18:54:17 +08:00
chenfeiyu
3ca037453e
remove conf and use yacs instead
2020-12-03 18:42:36 +08:00
chenfeiyu
4df5ad42f6
remove the last layer from decoder prenet
2020-12-03 15:55:07 +08:00
chenfeiyu
810f979dba
siwtch to keras style sample_weight in losses
2020-12-03 15:37:43 +08:00
chenfeiyu
6edc7d8474
switch back to standard implementation of positional encoding
2020-12-03 14:54:32 +08:00
chenfeiyu
404add2caa
temporary fix for memory leak
2020-12-03 14:51:25 +08:00
chenfeiyu
9cb5c03069
transformer_tts, miscellaneous fixes
2020-12-01 18:13:30 +08:00
chenfeiyu
598d813908
fix a bug in config
2020-11-23 13:24:03 +08:00
iclementine
2ed26d3416
do not expand the last layer of lists
2020-11-20 16:17:24 +08:00
iclementine
ce29ac68b3
use yaml instead of ruamel.yaml
2020-11-20 16:13:05 +08:00
iclementine
d190ce8d7f
use dict comprehension to exclude unspecified options
2020-11-20 15:21:06 +08:00
iclementine
6101c6ac86
fix typos
2020-11-20 15:18:53 +08:00
iclementine
5e11ce0dcd
remove options not specified via CLI before merging args
2020-11-20 15:17:35 +08:00
iclementine
73a2cadc36
remove default values when adding config options to a parser
2020-11-20 15:13:24 +08:00
iclementine
8af831ae3c
add --config by default when adding config options to a parser
2020-11-20 15:06:07 +08:00
iclementine
5b5eaaadac
add a tool for configuration
2020-11-20 14:33:56 +08:00
iclementine
fb49c1e77d
fix typos
2020-11-19 22:20:31 +08:00
iclementine
2dce0887b3
add schedulers
2020-11-19 22:17:50 +08:00
iclementine
49231ca8e5
move datasets
2020-11-19 22:04:25 +08:00
iclementine
db7598c702
add datasets
2020-11-19 20:43:03 +08:00
iclementine
abee3ecdd4
move datasets into parakeet.datasets
2020-11-19 20:31:21 +08:00
iclementine
b65cc4d8dc
add Unit normalizer
2020-11-19 20:17:42 +08:00
iclementine
a01200e437
add an cli for cloning examples
2020-11-19 18:08:11 +08:00
chenfeiyu
a9177cd6c2
waveflow: explicitly call forward hook before calling a method other than forward when needed.
2020-11-09 15:46:27 +08:00
chenfeiyu
af4da7dd9e
1. update code for waveflow's probability density estimation and sampling;
...
2. add WaveFlowLoss.
2020-11-04 23:22:45 +08:00
chenfeiyu
e07441c193
waveflow refactor: add prediction functionalities
2020-11-04 19:31:36 +08:00
chenfeiyu
8094578f6d
update waveflow to 2.0 APIs
2020-11-04 01:37:49 +08:00
chenfeiyu
0cdad602e2
fix a bug for changing reduction factor in transformner_tts
2020-11-03 11:18:46 +08:00
chenfeiyu
1f71f65c28
Merge branch 'reborn' into exp
2020-10-30 21:44:06 +08:00
chenfeiyu
68f5e1de15
add utility to pack attention weights
2020-10-30 21:36:11 +08:00
chenfeiyu
45d6f3b99d
specify a U(-.05, .05) initializer for Embedding
2020-10-30 17:42:06 +08:00
chenfeiyu
57d820f055
add support for channel last in batch_spec, and Conv1dBatchNorm
2020-10-30 15:13:57 +08:00
chenfeiyu
36cc543348
minor fixes to TransformerTTS
2020-10-28 11:05:47 +08:00
chenfeiyu
c43216ae9b
1. API renaming Conv1d -> Conv1D, BatchNorm1d -> BatchNorm1D;
...
2. add losses in parakeet/modules;
3. fix a bug in phonetics;
4. TransformerTTS update: encoder dim can be different from decoder dim;
5. MultiHeadAttention in TransformerTTS: add k_input_dim & v_input_dim in __init__ to allow differemt feature sizes for k and v.
2020-10-22 05:04:45 +00:00
iclementine
580655f33f
add phonetics & vocab & punctuation
2020-10-20 16:06:11 +08:00
iclementine
c1e0aecdde
1. import models into parakeet.models;
...
2. add predict for TransformerTTS and test its io.
2020-10-16 13:51:56 +08:00
iclementine
6aa7af1aa4
add AudioFolderDataset
2020-10-15 23:15:27 +08:00
iclementine
53d0382fc7
clean code: remove deprecated modules
2020-10-15 23:07:30 +08:00
iclementine
5270774bb0
tested io for TransformerTTS
2020-10-15 22:48:09 +08:00
iclementine
40457227e6
move Conv1dBatchNorm to conv.py
2020-10-14 10:05:26 +08:00
iclementine
f9087ea9a2
add masking functions
2020-10-13 15:53:18 +08:00
iclementine
a8192c79cc
WIP: refactor
2020-10-10 15:51:54 +08:00
liuyibing01
610181d4c0
Merge branch 'develop' into 'master'
...
dv3 miscellaneous enhancements.
See merge request !67
2020-07-29 12:21:49 +08:00
chenfeiyu
ddf1c4f7a7
1. fix initializers;
...
2. use simple random sampler;
3. clean code for gradient clipper.
2020-07-29 11:54:47 +08:00
Yibing Liu
47915461fc
Adapt waveflow to internal dataset
2020-07-28 17:34:38 +00:00
chenfeiyu
282c36c2c1
dv3 reloaded, back to the origin
2020-07-10 20:22:43 +08:00
lifuchen
abdc0a729f
Merge branch 'master' of upstream into commit
2020-06-23 12:53:36 +00:00
lifuchen
aaae100854
modified data preprocessing and synthesis of transformer_tts and fastspeech
2020-06-23 12:52:58 +00:00
liuyibing01
11f94b4f63
Merge branch 'fix' into 'master'
...
fix WeightNormWrapper, stop using CacheDataset for deep voice 3, pin numba version to 0.47.0
See merge request !59
2020-06-12 18:06:51 +08:00
chenfeiyu
45af3a43b2
fix WeightNormWrapper, stop using CacheDataset for deep voice 3, pin numba version to 0.47.0
2020-06-12 10:01:22 +00:00
liuyibing01
c170b5a282
Merge branch 'commit' into 'master'
...
fix some bugs of transformer_tts and fastspeech.
See merge request !58
2020-06-12 16:55:39 +08:00
lifuchen
681d34b953
fix some bugs of transformer_tts and fastspeech.
2020-06-12 08:54:32 +00:00
Yibing Liu
33ed693ccf
Upgrade waveflow api to 1.8.2
2020-06-12 08:45:55 +00:00
Yibing Liu
9b8fd9f93d
Upgrade waveflow to 1.8.0
2020-05-22 07:16:45 +00:00
liuyibing01
8716a1843c
Merge branch 'refactor' into 'master'
...
refactor for deep voice 3, update wavenet and clarinet to use enable_dygraph
See merge request !53
2020-05-22 14:28:57 +08:00
chenfeiyu
6aac18278e
refactor for deep voice 3, update wavenet and clarinet to use enable_dygraph
2020-05-20 12:37:19 +00:00