dan
/
tacotron2
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Commit Graph

  • 185cd24 (HEAD -> master) waveglow: updating waveglow submodule by rafaelvalle 2020-06-11 14:44:10 -0700
  • 0102db2 README.md: updating waveglow published model by Rafael Valle 2020-05-16 22:37:52 -0700
  • 6f435f7 updating waveglow submodule by rafaelvalle 2020-05-13 22:02:47 -0700
  • dd49ffa Merge pull request #143 from taras-sereda/master by Rafael Valle 2020-03-18 09:42:35 -0700
  • 2f2ed63 Merge pull request #279 from sih4sing5hong5/patch-1 by Rafael Valle 2020-03-18 09:41:32 -0700
  • 604e74d Merge pull request #313 from NVIDIA/dependabot/pip/tensorflow-1.15.2 by Rafael Valle 2020-03-17 10:15:45 -0700
  • dbd477b build(deps): bump tensorflow from 1.12.0 to 1.15.2 by dependabot[bot] 2020-03-09 21:31:38 +0000
  • 91ae5b5 Update requirements.txt by Rafael Valle 2020-03-09 14:31:11 -0700
  • 2583315 Merge pull request #303 from NTT123/fix-batch-size-1 by Rafael Valle 2020-02-10 13:43:47 -0800
  • ca5a22a Merge pull request #304 from NTT123/remove-tensorboardX by Rafael Valle 2020-02-10 13:43:11 -0800
  • 438b939 remove tensorboardX; use torch.utils.tensorboard by ntt123 2020-02-10 16:15:55 +0800
  • 14dbc37 fix error when batch size = 1 by ntt123 2020-02-10 16:07:00 +0800
  • 6d0635e train.py: printing correct variable by Rafael Valle 2020-01-09 01:37:57 -0800
  • a513db5 utils.py: compatibility with new pytorch by Rafael Valle 2019-12-11 16:53:20 -0800
  • 37a033d logger.py: compatibility with new tensorboardX by Rafael Valle 2019-12-11 16:53:02 -0800
  • 53a97e8 [bug-fix] pillow dependency in Dockerfile by 薛丞宏 2019-11-01 14:21:00 +0800
  • 70d37f9 train.py: reporting the right variable by Rafael Valle 2019-10-25 21:45:37 -0700
  • 131c146 Merge pull request #188 from jybaek/fixed-waveglow-link by Rafael Valle 2019-04-22 16:49:14 -0700
  • d5321ff Fixed link to download waveglow from inference.py by jybaek 2019-04-19 15:21:09 +0900
  • c76ac3b README.md: clarifying terminology by rafaelvalle 2019-04-03 14:59:20 -0700
  • e3d2d0a README.md: using proper nomenclature by rafaelvalle 2019-04-03 14:56:06 -0700
  • a992aea README.md: updating terminology by rafaelvalle 2019-04-03 14:54:45 -0700
  • eb2a171 Merge branch 'master' of https://github.com/NVIDIA/tacotron2 by rafaelvalle 2019-04-03 13:51:59 -0800
  • 821bfeb README.md: adding instructions to install apex by rafaelvalle 2019-04-03 13:51:36 -0800
  • d6670c8 Dockerfile: updating to use latest pytorch and apex by rafaelvalle 2019-04-03 13:51:22 -0800
  • 0274619 train.py: using amp for mixed precision training by rafaelvalle 2019-04-03 13:42:00 -0800
  • bb20035 inference.ipynb: adding fp16 inference by rafaelvalle 2019-04-03 13:41:11 -0800
  • 1480f82 model.py: renaming variables, removing dropout from lstm cell state, removing conversions now handled by amp by rafaelvalle 2019-04-03 13:36:35 -0800
  • 087c867 logger.py: using new pytorch api by rafaelvalle 2019-04-03 13:35:04 -0800
  • ece7d3f train.py: changing dataloder params given sampler by Rafael Valle 2019-03-19 13:47:01 -0700
  • f37998c train.py: shuffling at every epoch by rafaelvalle 2019-03-15 17:49:27 -0700
  • bff304f README.md: adding explanation on training from pre-trained model by rafaelvalle 2019-03-15 17:38:40 -0700
  • 3869781 train.py: adding routine to warm start and ignore layers, e.g. embedding.weight by rafaelvalle 2019-03-15 17:34:27 -0700
  • bb67613 hparams.py: adding ignore_layers argument to ignore text embedding layers when warm_starting by rafaelvalle 2019-03-15 17:28:50 -0700
  • af1f71a inference.ipynb: adding code to remove waveglows bias by rafaelvalle 2019-03-15 16:54:54 -0700
  • fc0d34c stft.py: moving window_sum to cuda if magnitude is cuda by rafaelvalle 2019-03-15 14:36:56 -0700
  • 5f03d07 seed from hparams for TextMelLoader by Taras Sereda 2019-02-14 10:10:58 +0200
  • f2c94d9 Merge pull request #136 from GrzegorzKarchNV/master by Rafael Valle 2019-02-01 12:10:42 -0800
  • df4a466 Fixing concatenation error for fp16 ditributed training by gkarch 2019-02-01 09:55:59 +0100
  • 825ffa4 inference.ipynb: reverting fp16 inference for now by rafaelvalle 2018-12-08 21:26:01 -0800
  • 4d7b041 inference.ipynb: changing waverglow inference fo fp16 by rafaelvalle 2018-12-05 22:14:35 -0800
  • 6e43055 train.py: val logger on gpu 0 only by rafaelvalle 2018-11-27 22:03:11 -0800
  • 3973b3e hparams.py: distributed using tcp by rafaelvalle 2018-11-27 22:02:43 -0800
  • 52a30bb distributed.py: replacing to avoid distributed error by rafaelvalle 2018-11-27 21:01:26 -0800
  • 0ad65cc train.py: renaming variable to n_gpus by rafaelvalle 2018-11-27 21:00:05 -0800
  • 8300844 hparams.py: removing 22khz by rafaelvalle 2018-11-27 20:56:52 -0800
  • f06063f train.py: renaming function, removing dataparallel by rafaelvalle 2018-11-27 18:04:12 -0800
  • 3045ba1 inference.ipynb: cleanup by rafaelvalle 2018-11-27 12:04:36 -0800
  • 4c4aca3 README.md: layout by rafaelvalle 2018-11-27 11:59:05 -0800
  • 05dd8f9 README.md: adding submodule init to README by rafaelvalle 2018-11-27 11:55:40 -0800
  • 5d66c3d adding waveglow submodule by rafaelvalle 2018-11-27 11:53:20 -0800
  • f02704f Merge pull request #96 from NVIDIA/clean_slate by Rafael Valle 2018-11-27 08:06:00 -0800
  • ba8cf36 requirements.txt: removing pytorch 0.4 from requirements. upgrading to 1.0 by rafaelvalle 2018-11-27 08:04:21 -0800
  • b5e0a93 inference.ipynb: updating inference file with relative paths by rafaelvalle 2018-11-27 08:04:04 -0800
  • 58b0ec6 README.md: updating requirements and inference demo by rafaelvalle 2018-11-27 08:03:34 -0800
  • 1ad939d inference.ipynb: setting relative model paths by rafaelvalle 2018-11-27 07:45:09 -0800
  • 32b9a13 utils.py: updating by rafaelvalle 2018-11-25 22:34:38 -0800
  • ce29e13 train.py: updating by rafaelvalle 2018-11-25 22:34:34 -0800
  • 1ea6ed5 text/symbols.py: updating symbols by rafaelvalle 2018-11-25 22:34:26 -0800
  • cdfde98 text/__init__.py: remove stop token by rafaelvalle 2018-11-25 22:34:11 -0800
  • e314bb4 stft.py: fix filter winlength error by rafaelvalle 2018-11-25 22:33:52 -0800
  • 4af4ccb model.py: rewrite by rafaelvalle 2018-11-25 22:33:38 -0800
  • 1ec0e5e layers.py: rewrite by rafaelvalle 2018-11-25 22:33:32 -0800
  • 249afd8 inference.ipynb: import taco2model to be public by rafaelvalle 2018-11-25 22:33:16 -0800
  • 1b243d5 hparams.py:rewrite by rafaelvalle 2018-11-25 22:33:05 -0800
  • d0aa9e7 distributed.py: rewrite by rafaelvalle 2018-11-25 22:32:54 -0800
  • 1683a57 data_utils.py: rewrite by rafaelvalle 2018-11-25 22:32:47 -0800
  • fc0cf6a Merge pull request #53 from cobr123/patch-1 by Rafael Valle 2018-07-02 14:32:21 -0700
  • 8de3849 add pillow by cobr123 2018-07-02 19:35:51 +0300
  • 7eb0452 README.md: updating readme to explicitly mention that mel representation of WaveNet and Tacotron2 must be the same by rafaelvalle 2018-06-14 11:25:42 -0700
  • c67005f Dockerfile: adding jupyter to dockerfile by rafaelvalle 2018-06-14 10:30:01 -0700
  • cb37947 Dockerfile: removing return from Dockerfile by rafaelvalle 2018-06-12 21:38:03 -0700
  • a8de973 Merge pull request #37 from yoks/master by Rafael Valle 2018-06-12 09:00:14 -0700
  • a0ae2da `used_saved_learning_rate` fix by yoks 2018-06-12 16:53:12 +0300
  • 34066ac requirements.txt: setting torch to 0.4.0 by rafaelvalle 2018-06-11 08:16:31 -0700
  • 12ab5ba model.py: setting weight initialization to xavier uniform by rafaelvalle 2018-06-07 20:28:52 -0700
  • d10da5f hparams.py: commenting n_frames_per_step to indicate that currently only 1 frame per step is supported now by rafaelvalle 2018-06-07 13:02:23 -0700
  • 5f0ea06 hparams.py: adding use saved learning rate param by rafaelvalle 2018-06-05 08:12:49 -0700
  • 22bcff1 hparams.py: adding use saved learning rate param by rafaelvalle 2018-06-05 08:12:35 -0700
  • 2e93447 README.md: being explicit about action by rafaelvalle 2018-06-04 17:12:32 -0700
  • 8ae231b README.md: more explicit about demo audio by rafaelvalle 2018-06-04 16:56:22 -0700
  • 4d733d1 README.md: including demo.wav in readme by rafaelvalle 2018-06-04 16:55:17 -0700
  • b4e5240 adding demo.wav file by rafaelvalle 2018-06-04 16:46:36 -0700
  • 064629c Merge pull request #23 from NVIDIA/attention_full_mel by Rafael Valle 2018-05-20 12:25:54 -0700
  • d5b6472 model.py: moving for better readibility by Rafael Valle 2018-05-20 12:22:06 -0700
  • 977cb37 model.py: attending to full mel instead of prenet and dropout mel by Rafael Valle 2018-05-18 06:59:09 -0700
  • da30fd8 Merge pull request #20 from NVIDIA/fp16_path by Rafael Valle 2018-05-15 09:55:19 -0700
  • 27b1767 train.py: fixing typo by Rafael Valle 2018-05-15 09:53:33 -0700
  • 817cd40 Merge branch 'master' of https://github.com/NVIDIA/tacotron2 into load_mel_from_disk by Rafael Valle 2018-05-15 09:51:41 -0700
  • 1071023 train.py: patching score_mask_value formerly inf, not concrete value, for compatibility with pytorch by Rafael Valle 2018-05-15 09:50:56 -0700
  • cd85158 loss_scaler.py: patching loss scaler for compatibility with current pytorch by Rafael Valle 2018-05-15 09:50:08 -0700
  • bd42cb6 Merge pull request #19 from NVIDIA/load_mel_from_disk by Rafael Valle 2018-05-15 08:54:24 -0700
  • 2da7a2e README.md: describing how to load mel from disk by Rafael Valle 2018-05-15 08:50:21 -0700
  • 62d2c8b data_utils.py: adding support for loading mel from disk by Rafael Valle 2018-05-15 08:42:06 -0700
  • 2d41ea0 hparams.py: adding load_mel_from_disk params by Rafael Valle 2018-05-15 08:41:03 -0700
  • 2056864 Merge branch 'master' of https://github.com/NVIDIA/tacotron2 by Rafael Valle 2018-05-06 08:58:07 -0700
  • dcd925f model.py: mixed squeeze target. fixing by Rafael Valle 2018-05-06 08:58:01 -0700
  • 4ac6ce9 ipynb typo by Raul Puri 2018-05-05 17:30:08 -0700
  • c67ca65 force single gpu in inference.ipynb by Raul Puri 2018-05-05 17:29:09 -0700
  • 78d5150 inference (distributed) dataparallel patch by Raul Puri 2018-05-05 17:23:11 -0700