Commit Graph

148 Commits

Author SHA1 Message Date
Hui Zhang ffcafb9b18
Revert "Add models/fastspeech2" 2021-06-16 14:21:24 +08:00
chenfeiyu 643dfa0fa0 WIP: add models/fastspeech2 2021-06-16 10:57:53 +08:00
chenfeiyu 3aa6aed0fb fix a config key error 2021-05-18 18:57:13 +08:00
Feiyu Chan 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
chenfeiyu 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
lfchener 80bf04b710 fix the behavior of dropout in eval of tacotron2 2020-12-28 08:28:55 +00:00
chenfeiyu 2421a936ed fix positional encoding naming conflict 2020-12-21 17:41:18 +08:00
iclementine e03e96d9e4 format all the code with yapf 2020-12-20 13:15:07 +08:00
iclementine f31643b33c 1. fix typos;
2. add tensorboardX into install requirements.
2020-12-19 20:08:25 +08:00
iclementine b6efb43990 update docstring for waveflow 2020-12-19 18:33:07 +08:00
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 1af9127ee6 add docstring for LocationSensitiveAttention 2020-12-18 17:31:51 +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 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 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
lfchener 09f1840082 fix some bugs of tacotron2 2020-12-11 03:56:40 +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 62959759f9 add linear in decoder prenet 2020-12-05 22:09:44 +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 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 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
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 45d6f3b99d specify a U(-.05, .05) initializer for Embedding 2020-10-30 17:42:06 +08:00