5b93de8a2e
fix EnglishCharacter frontend, add space in sentence ids
2020-12-14 08:57:08 +00:00
3a19150344
move model.eval() to manually
2020-12-12 10:34:48 +00:00
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
026ae1078b
add from_pretrained function for tacotron2 and support synthesize
2020-12-12 08:09:15 +00:00
99fdd10b5d
add plot alignment function
2020-12-11 12:04:32 +00:00
4de58f4a99
Merge pull request #48 from iclementine/reborn
...
add set_device at experiment setup
2020-12-11 19:50:27 +08:00
a079e767df
add set_device at experiment setup
2020-12-11 19:45:49 +08:00
1d2e93c75f
Merge pull request #45 from lfchener/reborn
...
add TTS model tacotron2
2020-12-11 16:33:22 +08:00
a8b10f50fb
fix EnglishCharacter numericalize in phonectic.py
2020-12-11 08:31:34 +00:00
cecc8735c4
1. fix ExperimentBase, create ouput folder with parent,
...
2. fix stop condition
2020-12-11 11:58:57 +08:00
09f1840082
fix some bugs of tacotron2
2020-12-11 03:56:40 +00:00
fb64c79f7a
add normalize function in normalizer.py
2020-12-10 07:05:40 +00:00
e30d7ad48f
merge upstream develop
2020-12-10 03:37:56 +00:00
a1b827460c
fix typos, move quantize/dequantize to moduels/audio
2020-12-09 21:05:39 +08:00
f375792c51
add tacotron2.py and a new frontend for en
2020-12-09 12:42:41 +00:00
e29502f634
Merge branch 'reborn' of https://github.com/iclementine/Parakeet into reborn
2020-12-09 09:08:46 +00:00
b12eda8423
add network of tacotron2 model
2020-12-09 09:08:17 +00:00
29cc759241
add access control by __all__ in modules
2020-12-09 15:58:39 +08:00
4893c9c086
add an ExperimentBase class and default config for training
2020-12-08 15:46:41 +08:00
37d4475810
add default argument parser
2020-12-08 10:56:47 +08:00
62959759f9
add linear in decoder prenet
2020-12-05 22:09:44 +08:00
0287f46532
switch back to keras style sample weight
2020-12-05 21:08:10 +08:00
d3761683e1
add an adaptive loss to balance stop prediction classes
2020-12-05 14:12:30 +08:00
a4a0bd8c98
add last bn for the decoder postnet, switch back to weighted mean
2020-12-05 14:00:08 +08:00
c57e8e7350
fix transformer_tts' stop condition
2020-12-04 02:11:02 +08:00
e87bfb7d05
hide fastspeech, deepvoice3, clarinet temporarily till they are updated
2020-12-03 18:54:17 +08:00
3ca037453e
remove conf and use yacs instead
2020-12-03 18:42:36 +08:00
4df5ad42f6
remove the last layer from decoder prenet
2020-12-03 15:55:07 +08:00
810f979dba
siwtch to keras style sample_weight in losses
2020-12-03 15:37:43 +08:00
6edc7d8474
switch back to standard implementation of positional encoding
2020-12-03 14:54:32 +08:00
404add2caa
temporary fix for memory leak
2020-12-03 14:51:25 +08:00
9cb5c03069
transformer_tts, miscellaneous fixes
2020-12-01 18:13:30 +08:00
598d813908
fix a bug in config
2020-11-23 13:24:03 +08:00
2ed26d3416
do not expand the last layer of lists
2020-11-20 16:17:24 +08:00
ce29ac68b3
use yaml instead of ruamel.yaml
2020-11-20 16:13:05 +08:00
d190ce8d7f
use dict comprehension to exclude unspecified options
2020-11-20 15:21:06 +08:00
6101c6ac86
fix typos
2020-11-20 15:18:53 +08:00
5e11ce0dcd
remove options not specified via CLI before merging args
2020-11-20 15:17:35 +08:00
73a2cadc36
remove default values when adding config options to a parser
2020-11-20 15:13:24 +08:00
8af831ae3c
add --config by default when adding config options to a parser
2020-11-20 15:06:07 +08:00
5b5eaaadac
add a tool for configuration
2020-11-20 14:33:56 +08:00
fb49c1e77d
fix typos
2020-11-19 22:20:31 +08:00
2dce0887b3
add schedulers
2020-11-19 22:17:50 +08:00
49231ca8e5
move datasets
2020-11-19 22:04:25 +08:00
db7598c702
add datasets
2020-11-19 20:43:03 +08:00
abee3ecdd4
move datasets into parakeet.datasets
2020-11-19 20:31:21 +08:00
b65cc4d8dc
add Unit normalizer
2020-11-19 20:17:42 +08:00
a01200e437
add an cli for cloning examples
2020-11-19 18:08:11 +08:00
a9177cd6c2
waveflow: explicitly call forward hook before calling a method other than forward when needed.
2020-11-09 15:46:27 +08:00
af4da7dd9e
1. update code for waveflow's probability density estimation and sampling;
...
2. add WaveFlowLoss.
2020-11-04 23:22:45 +08:00
e07441c193
waveflow refactor: add prediction functionalities
2020-11-04 19:31:36 +08:00
8094578f6d
update waveflow to 2.0 APIs
2020-11-04 01:37:49 +08:00
0cdad602e2
fix a bug for changing reduction factor in transformner_tts
2020-11-03 11:18:46 +08:00
1f71f65c28
Merge branch 'reborn' into exp
2020-10-30 21:44:06 +08:00
68f5e1de15
add utility to pack attention weights
2020-10-30 21:36:11 +08:00
45d6f3b99d
specify a U(-.05, .05) initializer for Embedding
2020-10-30 17:42:06 +08:00
57d820f055
add support for channel last in batch_spec, and Conv1dBatchNorm
2020-10-30 15:13:57 +08:00
36cc543348
minor fixes to TransformerTTS
2020-10-28 11:05:47 +08:00
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
580655f33f
add phonetics & vocab & punctuation
2020-10-20 16:06:11 +08:00
c1e0aecdde
1. import models into parakeet.models;
...
2. add predict for TransformerTTS and test its io.
2020-10-16 13:51:56 +08:00
6aa7af1aa4
add AudioFolderDataset
2020-10-15 23:15:27 +08:00
53d0382fc7
clean code: remove deprecated modules
2020-10-15 23:07:30 +08:00
5270774bb0
tested io for TransformerTTS
2020-10-15 22:48:09 +08:00
40457227e6
move Conv1dBatchNorm to conv.py
2020-10-14 10:05:26 +08:00
f9087ea9a2
add masking functions
2020-10-13 15:53:18 +08:00
a8192c79cc
WIP: refactor
2020-10-10 15:51:54 +08:00
610181d4c0
Merge branch 'develop' into 'master'
...
dv3 miscellaneous enhancements.
See merge request !67
2020-07-29 12:21:49 +08:00
ddf1c4f7a7
1. fix initializers;
...
2. use simple random sampler;
3. clean code for gradient clipper.
2020-07-29 11:54:47 +08:00
47915461fc
Adapt waveflow to internal dataset
2020-07-28 17:34:38 +00:00
282c36c2c1
dv3 reloaded, back to the origin
2020-07-10 20:22:43 +08:00
abdc0a729f
Merge branch 'master' of upstream into commit
2020-06-23 12:53:36 +00:00
aaae100854
modified data preprocessing and synthesis of transformer_tts and fastspeech
2020-06-23 12:52:58 +00:00
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
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
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
681d34b953
fix some bugs of transformer_tts and fastspeech.
2020-06-12 08:54:32 +00:00
33ed693ccf
Upgrade waveflow api to 1.8.2
2020-06-12 08:45:55 +00:00
9b8fd9f93d
Upgrade waveflow to 1.8.0
2020-05-22 07:16:45 +00:00
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
6aac18278e
refactor for deep voice 3, update wavenet and clarinet to use enable_dygraph
2020-05-20 12:37:19 +00:00
69b2a2b5cc
modified README of transformer_tts and fastspeech, remove dygraph.guard()
2020-05-09 03:11:55 +00:00
d1ba42ea68
modified fastspeech to make sure it works on paddle 1.8
2020-05-08 03:58:45 +00:00
55fa94f15d
Merge branch 'master' of upstream.
2020-05-08 03:47:40 +00:00
e0ba85f6b5
update for wavenet and clarinet
2020-05-08 03:33:27 +00:00
46e254d1f8
modified transformer_tts to make sure it works on paddle 1.8
2020-05-07 02:23:50 +00:00
ff1d66ea94
update for deepvoice3, fix weight norm
2020-05-06 08:36:43 +00:00
c1b837dc17
completed fastspeech and modified save/load
2020-04-09 12:06:04 +00:00
f312b2f05c
Merge branch 'master' of upstream
2020-04-07 09:34:39 +00:00
ad4b248af8
fix some bug of mask in fastspeech
2020-04-07 09:34:27 +00:00
838d6d1021
update save/load and README for deepvoice3, wavenet and clarinet
2020-03-26 10:43:27 +00:00
cf17b64983
Merge branch 'master' of upstream
2020-03-26 10:30:19 +00:00
618eb31ab4
Adapt the change in save & load
2020-03-26 09:27:22 +00:00
fccbf6d797
Update README
2020-03-26 06:45:22 +00:00
c845fbd51d
change interface for io.py
2020-03-26 10:10:05 +08:00
64790853e5
Unify save & load interfaces
2020-03-22 08:05:05 +00:00
be70b41fd1
Merge branch 'master' into 'master'
...
fixes for wavenet and modules
See merge request !47
2020-03-22 11:44:42 +08:00
2a1819a19c
add warning in Conv1DCell and synthesis.py for wavenet and deepvoice 3(auto-regressive models)
2020-03-21 15:10:25 +00:00
67613951d5
minor fixes for wavent and modules
2020-03-21 11:52:15 +00:00
75d464221c
modified the process of generating masks to speed up batching
2020-03-20 09:37:49 +00:00
f618b21765
Add a comment before layer pad2d
2020-03-13 06:05:57 +00:00
bfbc5e2046
Upgrade to paddle 1.7.1
2020-03-12 14:20:46 +00:00
4329b581f3
Merge branch 'master' into 'master'
...
add docstring for Conv1D, Conv1DTranspose and Conv1DCell, remove unnecessary file
See merge request !44
2020-03-10 17:06:05 +08:00
37390d96b9
add docstring for Conv1D, Conv1DTranspose and Conv1DCell, remove unnecessary file
2020-03-10 09:02:47 +00:00
384d093d47
Merge branch 'master' into 'master'
...
fix for compatability of python2 and lower versions of numpy
See merge request !42
2020-03-10 16:21:49 +08:00
af98dad33e
fix for compatability of python2 and lower versions of numpy
2020-03-10 08:17:56 +00:00
22cf0b82e8
Merge branch 'fix' into 'master'
...
fix the bug 1/x=0 in python2
See merge request !41
2020-03-10 14:56:21 +08:00
e720592ac1
fix the bug 1/x=0 in python2
2020-03-10 06:49:33 +00:00
c7176a8712
note on conv queue
2020-03-09 23:32:22 -07:00
c2cf81c38a
Merge branch 'master' into 'master'
...
add docstring to transformer_tts and fastspeech
See merge request !36
2020-03-10 11:25:55 +08:00
429695d6a0
add docstring to transformer_tts and fastspeech
2020-03-10 02:40:44 +00:00
6a9eab4b73
fix typos and refine doc
2020-03-09 15:33:13 +00:00
e0e40c5379
Merge branch 'master' of upstream.
2020-03-09 07:30:19 +00:00
484465ca1b
add docstring
2020-03-09 07:20:41 +00:00
e82115bc8a
Fix sample file name
2020-03-09 07:20:41 +00:00
f7ec215b9a
add docstring for transformer_tts and fastspeech
2020-03-09 07:16:02 +00:00
4b2b974eb4
refine docstring for parakeet.data and deep voice 3, wavenet and clarinet
2020-03-09 03:06:28 +00:00
4f7ded3c89
add docstring
2020-03-07 23:25:04 -08:00
8083da21ac
Fix sample file name
2020-03-07 14:21:35 +00:00
a302bf21f4
fix conflicts of dataset.py
2020-03-06 11:49:53 +00:00
fd009bb088
use os.path instead of pathlib.
2020-03-06 06:53:50 +00:00
86fff7a077
add doc for parakeet.data, python2 compatability for DataIterator and lazy CacheDataset
2020-03-06 02:55:42 +00:00
d08779d61e
Modified data.py to generate masks as models inputs
2020-03-05 07:22:50 +00:00
078d22e51c
Modified data.py to generate masks as models inputs
2020-03-05 07:08:12 +00:00
cd59c98637
Merge branch 'master' of upstream
2020-02-29 03:26:59 +00:00
b996e27f41
Temp fix bad get attr
2020-02-29 03:25:47 +00:00
44e61e0781
add missing parallel_wavenet, and fix python2 compatability
2020-02-28 03:24:24 +00:00
424c16a68d
staged clarinet
2020-02-27 10:23:05 +00:00
a012825423
refactor wavenet
2020-02-26 15:06:48 +00:00
9d79699432
add license
2020-02-26 21:03:51 +08:00
737d142ae4
Enable the fp16 inference for waveflow
2020-02-25 15:53:54 +00:00
87e12d26fa
Merge branch 'master' of upstream
2020-02-24 09:49:44 +00:00
ac437a080a
Remove unused modules.py
2020-02-24 09:49:10 +00:00
78582dbecd
make DataIterator compatible for python 2
2020-02-24 06:54:57 +00:00
8b051486f1
Update synthesis script for waveflow
2020-02-24 02:35:19 +00:00
7635493a0a
Remove unused code
2020-02-24 01:52:52 +00:00
f9d9785211
Update waveflow to 1.7 api and verified training
2020-02-23 19:00:17 +00:00
47d78b8739
remove utils.py to models/transdformer_tts
2020-02-20 02:17:25 +00:00
2bde79514a
deepvoice3: update logging functionalities
2020-02-17 14:53:37 +00:00
70e271ed95
deepvoice3: fix a bug in position embedding, fix initialization details for converter and attention.
2020-02-17 05:48:43 +00:00
5ad005fd9a
move data.py and rename some files
2020-02-16 17:54:11 +00:00
da9f3316c7
add missing imports in module/__init__.py
2020-02-16 17:54:11 +00:00
173693f469
fix missing imports, fix ljspeech.yaml config key: encoder_channels
2020-02-16 17:54:11 +00:00
6cbcadebda
add layer_tools
2020-02-16 17:54:11 +00:00
155dfe633d
add deepvoice3 model and example
2020-02-16 17:54:11 +00:00
04d7f8b598
transform parse to argparse
2020-02-13 06:48:21 +00:00
f5ac04b1a3
update Conv1D and Linear
2020-02-12 08:51:32 +00:00
53f569a519
customized.py
2020-02-11 12:38:35 +00:00
6908ec520c
Adjust the directory structure
2020-02-11 08:57:30 +00:00
fc84ca2d4b
Adjust the directory structure
2020-02-11 08:56:28 +00:00
lfchener
chenfeiyu
liuyibing01
lifuchen
Kexin Zhao
lifuchen