4a7888b8c6
complete theexample for speedyspeech; fix several bugs in training module
2021-07-12 15:19:22 +08:00
6c21d80025
add WIP: speedyspeech model and example with baker dataset.
2021-07-08 16:47:08 +08:00
7522c3eaba
remove tabs in default config file to avoid parsing error
2021-07-06 15:21:20 +08:00
fa0d7935d1
fix for script renaming
2021-07-01 19:29:39 +08:00
47a9ab3a0b
refine code, fix typos.
2021-07-01 18:59:01 +08:00
96b8e44015
Merge branch 'develop' of https://github.com/PaddlePaddle/Parakeet into use_mfa
2021-07-01 17:12:32 +08:00
68e9a84ada
Merge pull request #115 from iclementine/pwg
...
Add Parallel WaveGan and example
2021-07-01 04:04:52 -05:00
e41423caf0
avoid duplicated computation in validation, compute adversarial before stft loss.
2021-07-01 16:52:15 +08:00
3ebed00c96
minor fixes to refine code.
2021-07-01 16:14:55 +08:00
e6554abe05
make experiment dir
2021-07-01 15:55:28 +08:00
afe9d4a4f1
delete config for paralle training
2021-06-30 14:20:06 +08:00
dd6772bc3e
add --device to cli argument, use gpu by default
2021-06-30 13:57:05 +08:00
a93fad051c
auto choose device for inference
2021-06-30 13:50:41 +08:00
af26c1e389
fix priority in example/parallelwavegan
2021-06-30 13:33:56 +08:00
ef51e1ab13
refined training module
2021-06-30 13:08:23 +08:00
29b8b8b0ea
1. better error handling;
...
2. use absolute path in snapshot records;
3. visualdl takes a logger as init argument rather than creating one.
2021-06-27 18:53:45 +08:00
3e8a156348
add synthesis script for pwg
2021-06-26 19:31:52 +08:00
577c3b4f10
add use_mfa example
2021-06-25 07:31:40 +00:00
7e049a7744
add expanuser for preprocess, updater backward testing for pwg
2021-06-25 01:01:30 +08:00
542bbf6a81
add profiling tool and a config for parallel training
2021-06-24 14:53:38 +00:00
ea5cb8e71f
Dynamic to static
2021-06-23 15:18:37 +08:00
83c9f0aeae
add snapshot and visualizer
2021-06-21 09:56:26 +00:00
a738954001
1. change default data layout to channel last in preprocessing;
...
2. add Summary and DictSummary for aggrelation of evaluation losses;
3. add unittest for report ans scope.
2021-06-18 09:44:32 +00:00
fbc7e51fc9
1. add compute_statistics and normalize;
...
2. use jsonlines to read and write metadata by default;
3. use threadpool to replace processpool in preprocessing cause it is faster.
2021-06-18 02:49:49 +00:00
30045cf602
move synchronize up before timer starts
2021-06-17 03:12:35 +00:00
58a988c789
add code to compute statistics
2021-06-16 16:18:13 +00:00
042e02d242
use paddle's profiler
2021-06-16 13:43:13 +00:00
8dbcc9bccb
add profiling
2021-06-16 09:40:47 +00:00
bbbe5a8b50
add profiling
2021-06-16 14:47:30 +08:00
95f64c4f02
WIP: add some trainig info
2021-06-14 17:21:45 +08:00
b0983e4d76
WIP: pwg training works
2021-06-14 17:05:37 +08:00
54c7905f40
WIP: training setup done
2021-06-13 17:24:15 +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
7b0de356f9
fix experiments for waveflow and wavenet, only write visual log in rank-0
2021-02-21 17:34:11 +08:00
7c5e98dfb3
fix a bug when using a method other than forward with DataParallel
2021-01-11 17:24:46 +08:00
e53b9a0745
fix: the condition to init DataParallel
2021-01-11 17:17:31 +08:00
ddfe2eda76
fix attribute name for internal layer in DataParallel
2021-01-11 16:56:55 +08:00
737b09d03c
Merge pull request #72 from iclementine/example_readme
...
add README for transformer_tts, waveflow and wavenet
2020-12-30 15:56:46 +08:00
f5027a5e6f
fix typos again
2020-12-30 15:44:16 +08:00
d2dba13ab7
fix typos
2020-12-30 15:34:24 +08:00
3df4ecd455
add README for transformer_tts, waveflow and wavenet
2020-12-30 14:37:01 +08:00
d1d6c20672
add README for transformer_tts, waveflow and wavenet
2020-12-30 14:36:23 +08:00
46879b291b
add README for tacotron2
2020-12-29 03:33:08 +00:00
e03e96d9e4
format all the code with yapf
2020-12-20 13:15:07 +08:00
b6efb43990
update docstring for waveflow
2020-12-19 18:33:07 +08:00
0327874f19
add example for tacotron2
2020-12-18 19:59:34 +08:00
28fbc60737
add examples: transformer_tts, waveflow, wavenet
2020-12-18 19:51:55 +08:00
c7e5aaa540
remove old examples
2020-11-19 15:47:57 +08:00
1db01ccc90
Merge pull request #35 from ShenYuhan/fix_bug
...
fix bugs of vdl
2020-08-25 17:41:39 +08:00
3879b5ecb9
Merge pull request #22 from lfchener/fix
...
modified help massage of max_len in TransformerTTS synthesis
2020-08-25 17:38:47 +08:00
bb5f445212
fix bugs
2020-08-20 13:27:42 +08:00
ce8fad5412
Merge pull request #31 from ShenYuhan/add_vdl
...
add visualdl for parakeet
2020-08-20 11:39:17 +08:00
2933eb7e57
replace add_scalar to add_scalars
2020-08-14 17:48:24 +08:00
3717ac1342
add max_iteration into configuration, fix np.pad for lower versions of numpy
2020-08-11 09:22:08 +00:00
bf6d9ef06f
add visualdl for parakeet
2020-08-07 16:28:21 +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
de6e15339f
remove weigth norm when synthesizing to make inference fatser
2020-07-17 17:56:23 +08:00
60506d436a
add model architecture
2020-07-14 15:05:26 +08:00
8a5f9d75b6
update README and command line help msg
2020-07-14 11:33:15 +08:00
1eb9a273e9
modified help massage of max_len in TransformerTTS synthesis.
2020-07-13 15:36:21 +08:00
7938a5f6a4
add griffin lim as an alternative vocoder
2020-07-13 15:19:52 +08:00
282c36c2c1
dv3 reloaded, back to the origin
2020-07-10 20:22:43 +08:00
a333e64f79
modified README of transformer_tts and fastspeech
2020-06-24 03:27:45 +00:00
5b804b70e6
modified some config name and default path.
2020-06-24 02:52:22 +00:00
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
14235cd114
modified synthesis of transformer_tts & fastspeech
2020-06-19 03:46:10 +00:00
4eeece4158
Merge branch 'fix' into 'master'
...
fix synthesis for transformerTTS and FastSpeech, use int64 explicitly
See merge request !60
2020-06-12 18:14:48 +08:00
9dad6c3d41
fix synthesis for transformerTTS and FastSpeech, use int64 explicitly
2020-06-12 10:13:27 +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
9ba26facf0
deep coice 3: use np.int64 explicitly
2020-06-02 07:07:10 +00:00
aa8e4ea0a8
fix README for clarinet, pin numba and tqdm verison
2020-05-27 05:24:39 +00:00
74266afc2b
dv3: set p_replace_pronunciation to 0 at evaluation
2020-05-25 17:08:52 +08:00
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
45c07fa42e
modified fastspeech README
2020-04-14 06:16:17 +00:00
8505805dad
Fix init in synthesis & remove dry run
2020-04-13 11:31:39 +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
776743530a
update save & load for deep voicde 3, wavenet and clarinet, remove the concept of epoch in training
2020-03-25 01:37:17 +00:00
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
chenfeiyu
Hui Zhang
liangyunming
lfchener
iclementine
Li Fuchen
ShenYuhan
liuyibing01
lifuchen