Commits

Commits on Jul 23, 2018

Fix "RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument SeanNaren#4 'other'" for File "train.py", line 270, in <module> optimizer.step()
shuieryin
committedJul 23, 2018

Commits on Jul 14, 2018

Fixed benchmark script for variable lengths
sean.narenthiran
committedJul 14, 2018
Fixed curl cmd for server
sean.narenthiran
committedJul 14, 2018
Merge pull request SeanNaren#182 from EgorLakomkin/demo
Sean Naren
committedJul 14, 2018
Added debug level to server
sean.narenthiran
committedJul 14, 2018
Added docs, changes to update server file, refactored options
sean.narenthiran
committedJul 14, 2018

Commits on Jul 13, 2018

initial version of a flask sever serving deep speech model

EgorLakomkin
authored and
sean.narenthiran
committedJul 13, 2018

Commits on Jul 12, 2018

Merge pull request SeanNaren#323 from SeanNaren/multiproc
Sean Naren
committedJul 12, 2018
Added docs
sean.narenthiran
committedJul 12, 2018
Added ability to specify device IDs, added reduce operation for distribution to sync loss
sean.narenthiran
committedJul 12, 2018
Merge pull request SeanNaren#321 from SeanNaren/variable-length
Sean Naren
committedJul 12, 2018
Merge pull request SeanNaren#208 from EgorLakomkin/audio_norm
Sean Naren
committedJul 12, 2018
Normalizing audio within a 0-1 range

EgorLakomkin
authored and
sean.narenthiran
committedJul 12, 2018
Removed deprecated device-ids
sean.narenthiran
committedJul 12, 2018
Added proper cuda support for mask
sean.narenthiran
committedJul 12, 2018
Removed blacklist
sean.narenthiran
committedJul 12, 2018
Removed variables, added new masking layer, refactored training/loading of model
sean.narenthiran
committedJul 12, 2018

Commits on Jul 11, 2018

Changes to support variable length

SeanNaren
authored and
sean.narenthiran
committedJul 11, 2018

Commits on Jul 6, 2018

Merge pull request SeanNaren#318 from dalonlobo/master
Sean Naren
committedJul 6, 2018
Remove python parameter in multiproc
dalonlobo
committedJul 6, 2018
Update train.py
dalonlobo
committedJul 6, 2018

Commits on Jun 28, 2018

Merge pull request SeanNaren#311 from ggdupont/master
Sean Naren
committedJun 28, 2018

Commits on Jun 27, 2018

Updating env varible to ensure CTC lib is known
ggdupont
committedJun 27, 2018

Commits on May 20, 2018

Removed waffle badge
Sean Naren
committedMay 20, 2018
Merge pull request SeanNaren#294 from miguelvr/torch-update
Sean Naren
committedMay 20, 2018

Commits on May 8, 2018

Merge pull request SeanNaren#1 from SeanNaren/torch-update-fix
Miguel Varela Ramos
committedMay 8, 2018
Fix CUDA version for dockerfile, add jupyter support back, global grad set for test/transcribe and better creation of tensors for benchmark script
SeanNaren
committedMay 8, 2018

Commits on May 7, 2018

Fixed CTCDecoder convert_to_strings to work with torch==0.4 tensors
miguelvr
committedMay 7, 2018
Changes on syntax to support PyTorch v0.4

ryanleary
authored and
miguelvr
committedMay 7, 2018
Added ssh server capabilities to Dockerfile
miguelvr
committedMay 7, 2018

Commits on May 4, 2018

Added device-ids flag to train script
miguelvr
committedMay 4, 2018
Added tqdm progress bar for flac->wav conversion on librispeech script
miguelvr
committedMay 4, 2018
Modified docker file to run with torch=0.4
miguelvr
committedMay 4, 2018

Commits on Apr 20, 2018

Fix offsets flag
ryanleary
committedApr 20, 2018
Remove vestigial transpose to fix transcription
ryanleary
committedApr 20, 2018