Grzegorz Karch
|
4fe3b4e4ae
|
[Tacotron2/PyT] Using native amp
|
2021-11-08 14:23:50 -08:00 |
|
Adrian Lancucki
|
054fed043f
|
[FastPitch/PyT] Drop parselmouth dependency
|
2021-10-07 11:26:31 -07:00 |
|
Adrian Lancucki
|
6d762dacdc
|
rm unused filelists
|
2021-09-08 14:36:36 +00:00 |
|
Adrian Lancucki
|
b169ad3ba1
|
[FastPitch/PyT] Update NGC checkpoint url
|
2021-09-07 07:27:31 -07:00 |
|
Adrian Lancucki
|
ba8f04bfe2
|
[FastPitch/PyT] Add FastPitch 1.1 (autoaligned)
|
2021-08-23 22:52:23 +02:00 |
|
gkarch
|
793027c9da
|
removed triton stuff from model dockerfile and moved it to ./triton folder
|
2021-08-13 16:33:09 +00:00 |
|
Andrei Shumak
|
6a642837c4
|
Revert changes to FastPitch and BERT on PyTorch
|
2021-08-13 16:19:34 +02:00 |
|
Andrei Shumak
|
9ea704497c
|
[PyT] FastPitch: new CI configurations
|
2021-08-06 14:08:33 +00:00 |
|
Krzysztof Kudrynski
|
49e23b4597
|
Adding links to performance benchmark page
|
2021-07-21 14:39:48 +02:00 |
|
kkudrynski
|
81ee705868
|
[PyTorchHub] Adding licences to entrypoint scripts
|
2021-06-18 14:56:07 +00:00 |
|
Jan Golda
|
778583481b
|
[TorchHub] restructured hubconf and updated SSD and Tacotron2/WaveGlow entrypoints
|
2021-06-07 12:20:51 +00:00 |
|
Adrian Lancucki
|
8d8c524df6
|
[FastPitch/PyT] Fix updated regulate_len
|
2021-05-21 11:35:47 +02:00 |
|
Grzegorz Karch
|
5a8521ee05
|
[Tacotron2/PyT] rename common->tacotron2_common
|
2021-05-18 16:28:11 +00:00 |
|
Adrian Lancucki
|
0c04f3caaf
|
Update model description
|
2021-05-14 14:05:32 +02:00 |
|
kkudrynski
|
afe00719ca
|
[FastPitch/PyT] Added Triton
|
2021-04-13 16:18:11 +02:00 |
|
Adrian Lancucki
|
2b0daf392a
|
Update README.md
|
2021-02-19 17:47:01 +01:00 |
|
Shashank Verma
|
a1b789b829
|
Add PyT Speech Synthesis README
Signed-off-by: Shashank Verma <shashank3959@gmail.com>
|
2020-12-02 00:39:50 -08:00 |
|
gkarch
|
9a6c5241d7
|
fixing rng_state for backward compatibility
|
2020-11-19 14:21:05 +01:00 |
|
kkudrynski
|
ff86473b48
|
[FastPitch/PyT] Fixed ckpt handling
|
2020-11-05 13:42:03 +01:00 |
|
kkudrynski
|
bec82593f5
|
[FastPitch/PyT] updated checkpoints, multispeaker and text processing
|
2020-10-30 15:06:02 +01:00 |
|
kkudrynski
|
b2c72b284f
|
[FastPitch/PyT] Adding notebooks
|
2020-10-21 17:31:40 +02:00 |
|
GrzegorzKarchNV
|
70f247fc34
|
Merge pull request #700 from KsenijaS/fix_div
Fix integer division in Waveglow
|
2020-10-07 22:04:39 +02:00 |
|
gkarch
|
385d81eed0
|
a few fixes
|
2020-10-07 13:01:21 +02:00 |
|
gkarch
|
550123fbbc
|
updated convai
|
2020-10-07 11:39:45 +02:00 |
|
kkudrynski
|
d057babe5c
|
[FastPitch/PyT] Updating for 20.08
|
2020-09-30 13:23:05 +02:00 |
|
Ksenija Stanojevic
|
421c83952c
|
fix div
|
2020-09-24 21:13:07 -07:00 |
|
Tonmoay Deb
|
c480fbfcf6
|
[Tacotron2] fixed get_model in inference.py
|
2020-07-08 11:14:53 +06:00 |
|
Przemek Strzelczyk
|
77dad060a2
|
[FastPitch] Updating for Ampere
|
2020-07-04 02:24:45 +02:00 |
|
Przemek Strzelczyk
|
f0c8bc571a
|
[Tacotron2/PyT} Updating for Ampere
|
2020-07-04 01:15:57 +02:00 |
|
GrzegorzKarchNV
|
4f02f7af81
|
Update Dockerfile
|
2020-07-01 09:51:51 +02:00 |
|
Przemek Strzelczyk
|
4eaa4434de
|
[ConvNets/TF] Adding support for Ampere
|
2020-06-27 09:24:41 +02:00 |
|
Krzysztof Kudrynski
|
f11884b38a
|
minor readme updates
|
2020-06-12 13:50:44 +02:00 |
|
Przemek Strzelczyk
|
23cc1cd5bb
|
[FastPitch/PyT] Small README fixes
|
2020-06-12 12:13:05 +02:00 |
|
Przemek Strzelczyk
|
66ed01d1ac
|
[FastPitch/PyT] README updates
|
2020-06-08 18:53:02 +02:00 |
|
gkarch
|
fb6d73d8f5
|
updated README for Triton
|
2020-05-29 13:50:04 +02:00 |
|
gkarch
|
5d792121ba
|
remover tcmalloc from Dockerfile
|
2020-05-28 14:14:39 +02:00 |
|
gkarch
|
2480060f2a
|
added tcmalloc in Dockerfile
|
2020-05-27 15:26:19 +02:00 |
|
PrzemekS
|
7a2f7d4a55
|
Merge pull request #516 from NVIDIA/nvptr/6d7283
Adding FastPitch/PyT (modified version of FastSpeech)
|
2020-05-26 18:55:40 +02:00 |
|
Ilya Shutov
|
680ccfcf89
|
Tacotron2 --cpu-run fix
|
2020-05-21 21:05:24 +07:00 |
|
gkarch
|
3bddd5df99
|
updates MR78
|
2020-05-19 15:06:13 +02:00 |
|
Przemek Strzelczyk
|
6d72839a6c
|
Adding FastPitch/PyT (modified version of FastSpeech)
|
2020-05-18 18:49:00 +02:00 |
|
gkarch
|
1cfa0ecffb
|
small fixes
|
2020-05-18 12:08:59 +02:00 |
|
gkarch
|
53e7e4f130
|
updating trtis_cpp
|
2020-05-18 11:04:16 +02:00 |
|
gkarch
|
bf2b7a0767
|
fixed trtis dockerfile
|
2020-05-14 22:24:54 +02:00 |
|
gkarch
|
8d8337196f
|
fixed trtis
|
2020-05-14 19:58:45 +02:00 |
|
gkarch
|
86dc81241c
|
[Tacotron2] fixed load_and_setup_model in ONNX exports
|
2020-05-13 11:24:39 +02:00 |
|
gkarch
|
1272f6fafa
|
[Tacotron2] fixed get_model in train.py
|
2020-05-13 11:08:15 +02:00 |
|
maggiezha
|
387f700c4c
|
add Intel Optimization for PyTorch
Intel's optimization for PyTorch on CPU are added, you need to set "export OMP_NUM_THREADS=num physical cores" based on your CPU's core number
|
2020-05-07 15:57:07 +10:00 |
|
maggiezha
|
150f877e19
|
adding CPU optimization
export OMP_NUM_THREADS=num physical cores
export KMP_BLOCKTIME=0
export KMP_AFFINITY=granularity=fine,compact,1,0
https://software.intel.com/content/www/us/en/develop/articles/maximize-tensorflow-performance-on-cpu-considerations-and-recommendations-for-inference.html
|
2020-05-07 15:51:45 +10:00 |
|
GrzegorzKarchNV
|
67a7d9c4eb
|
Merge pull request #482 from maggiezha/cpu-run
Cpu run
|
2020-05-06 21:27:26 +02:00 |
|