malarinv
/
tacotron2
mirror of https://github.com/malarinv/tacotron2
1
0
Fork 0
Code Issues Releases Wiki Activity
147 Commits
10 Branches
0 Tags
3.3 MiB
Commit Graph

147 Commits (master)

Author SHA1 Message Date
Malar 6d3679d760 relax scipy version 2021-07-02 23:21:45 +05:30
Malar Kannan a851e80db2 1. added rpyc server optional package 
2. updated path variable
 2020-03-05 16:59:55 +05:30
Malar Kannan cb0c8ddd06 1. make pyaudio as extra requirement 
2. warn if pyaudio not installed if player_gen is used
 2020-01-22 14:09:37 +05:30
Malar 42a85d177e added glow as module 2019-11-29 00:20:01 +05:30
Malar 5efb1e2758 1. fix synth_speech_fast interface 
2. rename private methods
 2019-11-28 18:11:47 +05:30
Malar Kannan ea11c5199e tested gl/wavglow working 2019-11-28 18:00:52 +05:30
Malar 78eed2d295 bugfix for vocoder arg 2019-11-28 17:03:46 +05:30
Malar 009b87e716 update dependency version and add speed/sample rate and vocoder args 2019-11-28 16:57:36 +05:30
Malar Kannan ac5ffcf6d5 enable gpu support if available 2019-11-27 22:53:41 +05:30
Malar Kannan 5a30069f0a update tempo and output sample rate 2019-10-09 17:25:51 +05:30
Malar Kannan dcc9ab3625 add tts cli args 2019-10-09 16:23:21 +05:30
Malar Kannan dde35048b7 1. implemented corpus wav generator 
2. refactor
 2019-10-07 16:05:28 +05:30
Malar Kannan 36f229449f 1. remove unneeded files 
2. add Makefile
 2019-10-04 16:24:36 +05:30
Malar Kannan edbb1bd57d 1. clean-up 
2. update readme and release info
 2019-10-04 16:15:30 +05:30
Malar Kannan 36c731cad0 1. update waveglow 
2. add gl option and hyperparams to TTSModel
 2019-10-04 15:27:59 +05:30
Malar d0d273a698 add placeholder path to models 2019-10-02 00:44:03 +05:30
Malar acfcadac47 update setup.py artifact and add dunder files 2019-10-02 00:42:02 +05:30
Malar Kannan 0682eddfdc 1. add griffin lim support 
2. add denoiser
3. add support to handle old and new waveglow models
 2019-09-26 10:53:09 +05:30
Malar Kannan a10a6d517e packaged taco2 2019-09-21 01:19:30 +05:30
Malar Kannan 1f83e8687c implemented a grpc server for entity api 2019-07-16 16:01:08 +05:30
Malar Kannan 755362518a update comments 2019-07-16 16:01:08 +05:30
Malar Kannan 9413fb73b9 move codestyle to black 2019-07-16 16:01:08 +05:30
Malar Kannan 108ce2b079 cleanup unused code and fix packaging issues 2019-07-16 16:01:00 +05:30
Malar Kannan 5f75aa0a0d integrate tacotron2/waveglow based tts server 2019-07-16 16:00:50 +05:30
Malar Kannan 4be2475cc1 load waveglow model from statedict 2019-07-03 14:05:10 +05:30
Malar Kannan 08ad9ce16e 1. clean-up redundant code 
2. remove ffmpeg dependency using librosa api
3. remove waveglow submodule
 2019-07-02 16:16:44 +05:30
Malar Kannan 505af768a0 1. create a class for the tts api 
2. implement a grpc server for tts
3. add a demo client for the grpc service
4. update gitignore and requriements
5. cleanup
 2019-07-01 14:47:55 +05:30
Malar Kannan ccd8ab42e7 add a function to cache all responses from corpus.txt 2019-06-28 18:44:24 +05:30
Malar Kannan 102c424eac add WORKFLOW.md and update final.py 2019-06-28 14:24:36 +05:30
Malar Kannan 81d15abb4d return audio stream from speech 2019-06-28 10:25:37 +05:30
Malar Kannan acf1b444a9 clean-up for cpu-only inference 2019-06-28 09:46:46 +05:30
Rafael Valle 131c1465b4
Merge pull request #188 from jybaek/fixed-waveglow-link 
Fixed link to download waveglow from inference.py
 2019-04-22 16:49:14 -07:00
jybaek d5321ff0ca Fixed link to download waveglow from inference.py 2019-04-19 15:21:09 +09:00
rafaelvalle c76ac3b211 README.md: clarifying terminology 2019-04-03 14:59:20 -07:00
rafaelvalle e3d2d0a5ef README.md: using proper nomenclature 2019-04-03 14:56:06 -07:00
rafaelvalle a992aea070 README.md: updating terminology 2019-04-03 14:54:45 -07:00
rafaelvalle eb2a171690 Merge branch 'master' of https://github.com/NVIDIA/tacotron2 2019-04-03 13:51:59 -08:00
rafaelvalle 821bfeba5d README.md: adding instructions to install apex 2019-04-03 13:51:36 -08:00
rafaelvalle d6670c8ed7 Dockerfile: updating to use latest pytorch and apex 2019-04-03 13:51:22 -08:00
rafaelvalle 0274619e45 train.py: using amp for mixed precision training 2019-04-03 13:42:00 -08:00
rafaelvalle bb20035586 inference.ipynb: adding fp16 inference 2019-04-03 13:41:11 -08:00
rafaelvalle 1480f82908 model.py: renaming variables, removing dropout from lstm cell state, removing conversions now handled by amp 2019-04-03 13:36:35 -08:00
rafaelvalle 087c86755f logger.py: using new pytorch api 2019-04-03 13:35:04 -08:00
Rafael Valle ece7d3f568 train.py: changing dataloder params given sampler 2019-03-19 13:47:01 -07:00
rafaelvalle f37998c59d train.py: shuffling at every epoch 2019-03-15 17:49:27 -07:00
rafaelvalle bff304f432 README.md: adding explanation on training from pre-trained model 2019-03-15 17:38:40 -07:00
rafaelvalle 3869781877 train.py: adding routine to warm start and ignore layers, e.g. embedding.weight 2019-03-15 17:34:27 -07:00
rafaelvalle bb67613493 hparams.py: adding ignore_layers argument to ignore text embedding layers when warm_starting 2019-03-15 17:28:50 -07:00
rafaelvalle af1f71a975 inference.ipynb: adding code to remove waveglows bias 2019-03-15 16:54:54 -07:00
rafaelvalle fc0d34cfce stft.py: moving window_sum to cuda if magnitude is cuda 2019-03-15 14:36:56 -07:00