988d6d3268
add h5py utility to interact with numpy
2021-06-10 18:57:46 +08:00
6a8b3f92df
add AudioDataset and MelDataset
2021-06-10 16:26:09 +08:00
a0763986e2
add kbest ( #114 )
...
* add kbest
* fix typos
* remove unnecessary imports
* fix del fn
* fix typos
* add k-latest
2021-06-10 10:36:14 +08:00
3c964fde54
add parallel wavegan model
2021-06-10 04:08:05 +08:00
759999c738
STFT and MelScale: register filters as buffer.
2021-06-10 04:06:06 +08:00
c306f5c2b3
add k-latest
2021-06-10 03:39:54 +08:00
dc9040dd4d
fix typos
2021-06-10 02:45:45 +08:00
0114a808a2
fix del fn
2021-06-10 00:40:54 +08:00
13323bdf6a
remove unnecessary imports
2021-06-10 00:32:49 +08:00
37a66f1506
fix typos
2021-06-10 00:29:25 +08:00
b571b506c3
add kbest
2021-06-10 00:25:00 +08:00
3aa6aed0fb
fix a config key error
2021-05-18 18:57:13 +08:00
4f288a6d4f
add ge2e and tacotron2_aishell3 example ( #107 )
...
* hacky thing, add tone support for acoustic model
* fix experiments for waveflow and wavenet, only write visual log in rank-0
* use emb add in tacotron2
* 1. remove space from numericalized representation;
2. fix decoder paddign mask's unsqueeze dim.
* remove bn in postnet
* refactoring code
* add an option to normalize volume when loading audio.
* add an embedding layer.
* 1. change the default min value of LogMagnitude to 1e-5;
2. remove stop logit prediction from tacotron2 model.
* WIP: baker
* add ge2e
* fix lstm speaker encoder
* fix lstm speaker encoder
* fix speaker encoder and add support for 2 more datasets
* simplify visualization code
* add a simple strategy to support multispeaker for tacotron.
* add vctk example for refactored tacotron
* fix indentation
* fix class name
* fix visualizer
* fix root path
* fix root path
* fix root path
* fix typos
* fix bugs
* fix text log extention name
* add example for baker and aishell3
* update experiment and display
* format code for tacotron_vctk, add plot_waveform to display
* add new trainer
* minor fix
* add global condition support for tacotron2
* add gst layer
* add 2 frontend
* fix fmax for example/waveflow
* update collate function, data loader not does not convert nested list into numpy array.
* WIP: add hifigan
* WIP:update hifigan
* change stft to use conv1d
* add audio datasets
* change batch_text_id, batch_spec, batch_wav to include valid lengths in the returned value
* change wavenet to use on-the-fly prepeocessing
* fix typos
* resolve conflict
* remove imports that are removed
* remove files not included in this release
* remove imports to deleted modules
* move tacotron2_msp
* clean code
* fix argument order
* fix argument name
* clean code for data processing
* WIP: add README
* add more details to thr README, fix some preprocess scripts
* add voice cloning notebook
* add an optional to alter the loss and model structure of tacotron2, add an alternative config
* add plot_multiple_attentions and update visualization code in transformer_tts
* format code
* remove tacotron2_msp
* update tacotron2 from_pretrained, update setup.py
* update tacotron2
* update tacotron_aishell3's README
* add images for exampels/tacotron2_aishell3's README
* update README for examples/ge2e
* add STFT back
* add extra_config keys into the default config of tacotron
* fix typos and docs
* update README and doc
* update docstrings for tacotron
* update doc
* update README
* add links to downlaod pretrained models
* refine READMEs and clean code
* add praatio into requirements for running the experiments
* format code with pre-commit
* simplify text processing code and update notebook
2021-05-13 17:49:50 +08:00
6f1c534557
use exist_ok to ensure no conflict
2021-02-23 10:50:57 +08:00
e69ab88fe6
fix multiprocessing training: other processes have to wait untils the output directory in created.
2021-02-23 10:40:14 +08:00
c955c4192b
fix tensorboard error https://github.com/pytorch/fairseq/issues/2357
2021-02-18 19:53:58 +08:00
0af7402daa
add rank_zero_only for ExperimentBase.save
2021-02-18 19:33:41 +08:00
f423323bae
fix bugs with multiprocess training.
2021-02-18 19:09:54 +08:00
30e3b9172f
1. fix imports for renamed functions in position encoding;
...
2. fix dimension in MLPPrenet in transformer_tts;
3. use dropout also in inference in MLPPrenet in transformer_tts.
2021-02-03 14:24:29 +08:00
c321fcd098
polish documentation
2021-01-13 14:58:26 +08:00
641be1bc92
Merge branch 'develop' of github.com:iclementine/Parakeet into doc
2021-01-13 11:09:05 +08:00
c2a279c433
add documentation sections
2021-01-13 11:06:15 +08:00
b0ba6e7bf9
fix an encoding problem in windows
2021-01-08 02:47:43 +00:00
80bf04b710
fix the behavior of dropout in eval of tacotron2
2020-12-28 08:28:55 +00:00
2421a936ed
fix positional encoding naming conflict
2020-12-21 17:41:18 +08:00
bb64e4659a
discard opencc untill we find an easy solution to install it on windows
2020-12-20 13:46:45 +08:00
e03e96d9e4
format all the code with yapf
2020-12-20 13:15:07 +08:00
f31643b33c
1. fix typos;
...
2. add tensorboardX into install requirements.
2020-12-19 20:08:25 +08:00
18709adce8
update setup.py and version str
2020-12-19 18:55:42 +08:00
b6efb43990
update docstring for waveflow
2020-12-19 18:33:07 +08:00
f2a35a17d4
import normalizer into frontend
2020-12-19 16:20:41 +08:00
544594ec54
Merge pull request #63 from iclementine/doc
...
update docstrings for models.wavenet.
2020-12-18 20:57:28 +08:00
84ad4c9e65
1. update docstrings for models.wavenet;
...
2. remove unnecessary code;
3. fix typos
2020-12-18 20:55:27 +08:00
255ddcfe32
modified docstring of tacotron2
2020-12-18 20:28:21 +08:00
63285dc80f
add docstring for normalizer
2020-12-18 19:36:12 +08:00
c2bc4b0474
add docstring for phonectic and vocab
2020-12-18 19:31:44 +08:00
1af9127ee6
add docstring for LocationSensitiveAttention
2020-12-18 17:31:51 +08:00
dd2c5cc6c6
Merge pull request #59 from iclementine/doc
...
update docstrings
2020-12-18 16:12:56 +08:00
310366bb54
1. fix format errors and typos
2020-12-18 16:09:38 +08:00
3baffa5f4c
update link in docstring
2020-12-18 15:53:24 +08:00
6b8573898a
update docstring of tacotron2
2020-12-18 15:50:05 +08:00
ecdeb14a40
add docstring for tacotron2
2020-12-18 15:31:40 +08:00
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
49c9cb38be
use numpydoc instead of napoleon
2020-12-18 11:12:22 +08:00
bbc50faef2
add generated api_doc
2020-12-18 10:54:50 +08:00
b82217f50f
Merge pull request #55 from lfchener/reborn
...
fix EnglishCharacter frontend and add spectrogram plots
2020-12-17 11:16:12 +08:00
6420da6197
fix some bugs
2020-12-17 02:56:45 +00:00
bdf60bec39
fix wavenet inference shape
2020-12-16 00:22:43 +08:00
a5c81c75d5
fix add_spectrogram_plots
2020-12-15 11:27:11 +00:00
c864612dc3
plot spectrogram
2020-12-15 09:07:40 +00:00
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
chenfeiyu
Hui Zhang
lfchener
iclementine
Li Fuchen