- 02 5月, 2023 3 次提交
-
-
由 Daniel Povey 提交于
Fix download location in install_liblbfgs.sh
-
由 Daniel Povey 提交于
-
由 Daniel Povey 提交于
-
- 26 4月, 2023 2 次提交
-
-
由 Nickolay V. Shmyrev 提交于
* Fix matrix data offset for large matrices * Fix overflow in cudamatrix too
-
由 Yuriy Chernyshov 提交于
This continues the work started in #4809.
-
- 18 4月, 2023 1 次提交
-
-
由 Nickolay V. Shmyrev 提交于
function is not used anyway
-
- 20 2月, 2023 1 次提交
-
-
由 Yifan Yang 提交于
-
- 18 2月, 2023 4 次提交
-
-
由 Daniel Povey 提交于
Fix -Wdeprecated-copy from c++11
-
由 Yuriy Chernyshov 提交于
-
由 Daniel Povey 提交于
SRILM: allow bypassing download/extraction during automated installation
-
由 Daniel Povey 提交于
Do not use ADL to invoke std::binary_search
-
- 04 2月, 2023 1 次提交
-
-
由 Karel Vesely 提交于
- the audio data no longer exist in that path - the beamformer config was missing in 'ami/s5b', it's taken from 'ami/s5'
-
- 07 1月, 2023 2 次提交
-
-
由 Daniel Galvez 提交于
This is to fix a CI error. It appears that this is from using "ubuntu-latest" in the CI workflow. It got upgraded to ubuntu 22.04 automatically, and this doesn't have python2.7 by default.
-
由 Daniel Galvez 提交于
-
- 26 12月, 2022 1 次提交
-
-
由 Tanmay Jain 提交于
Fix "glossaries_opt" variable name at line number 39. It's misspelled due to which words in the glossaries weren't reserved while creating BPE.
-
- 13 12月, 2022 1 次提交
-
-
由 Daniel Galvez 提交于
* Remove unused variable. * cudadecoder: Make word alignment optional. For CTC models using word pieces or graphemes, there is not enough positional information to use the word alignment. I tried marking every unit as "singleton" word_boundary.txt, but this explodes the state space very, very often. See: https://github.com/nvidia-riva/riva-asrlib-decoder/issues/3 With the "_" character in CTC models predicting word pieces, we at the very least know which word pieces begin a word and which ones are either in the middle of the word or the end of a word, but the algorithm would still need to be rewritten, especially since "blank" is not a silence phoneme (it can appear between). I did look into using the lexicon-based word alignment. I don't have a specific complaint about it, but I did get a weird error where it couldn't create a final state at all in the output lattice, which caused Connect() to output an empty lattice. This may be because I wasn't quite sure how to handle the blank token. I treat it as its own phoneme, bcause of limitations in TransitionInformation, but this doesn't really make any sense. Needless to say, while the CTM outputs of the cuda decoder will be correct from a WER point of view, their time stamps won't be correct, but they probably never were in the first place, for CTC models.
-
- 11 12月, 2022 1 次提交
-
-
由 daanzu 提交于
-
- 07 12月, 2022 1 次提交
-
-
由 Yuriy Chernyshov 提交于
-
- 26 9月, 2022 1 次提交
-
-
由 xu-gaopeng 提交于
* Update run_blstm.sh fix bug aspire run_blstm.sh * Update egs/aspire/s5/local/nnet3/run_blstm.sh Co-authored-by: NCy 'kkm' Katsnelson <kkm@pobox.com> Co-authored-by: NCy 'kkm' Katsnelson <kkm@pobox.com>
-
- 20 9月, 2022 2 次提交
-
-
由 Kavya Manohar 提交于
Provide provision to pass subword separator as argument to make_position_dependent_subword_lexicon.py (#4794)
-
由 npovey 提交于
Co-authored-by: Nnpovey <you@example.com>
-
- 14 9月, 2022 1 次提交
-
-
由 bhuang 提交于
-
- 01 9月, 2022 2 次提交
-
-
由 Taku Takamatsu 提交于
-
由 Jonghwan Hyeon 提交于
Coauthored-By: NJonghwan Hyeon <hyeon0145@gmail.com>
-
- 28 8月, 2022 1 次提交
-
-
由 Agrover112 提交于
The example for the post-to-tacc fails , but with the correct of `ark:- |` there is no piping error
-
- 18 8月, 2022 2 次提交
-
-
由 Jan "yenda" Trmal 提交于
-
由 Jan "yenda" Trmal 提交于
* [infra] docker images automatically using gh * minor change
-
- 17 8月, 2022 4 次提交
-
-
由 Jan "yenda" Trmal 提交于
-
由 Jan "yenda" Trmal 提交于
-
由 Sourya Kakarla 提交于
* Set PYTHONUNBUFFERED=TRUE for wsj,tedlium To force stdout, stderr to be unbuffered for python scripts. Without this setting parts of the stream might be lost in a few cases. Relevant mainly for python versions <3.7. * Set PYTHONUNBUFFERED=TRUE for all recipes Add to path.sh in all except the already updated wsj, tedlium. To force stdout, stderr to be unbuffered for python scripts. Relevant mainly for python versions <3.7. * Set PYTHONUNBUFFERED=TRUE in remaining path.sh These files were missed by mistake in earlier commits. * Use 1 instead of TRUE for PYTHONUNBUFFERED
-
由 Michael McAuliffe 提交于
-
- 16 8月, 2022 3 次提交
-
-
由 Jan "yenda" Trmal 提交于
-
由 Jan "yenda" Trmal 提交于
* Fix missing cblas and lapack external symbols for netlib * Remaining Conda-forge changes * Fix indent * usleep using C+11 constructs * make codefactor happy Co-authored-by: NMichael McAuliffe <michael.e.mcauliffe@gmail.com>
-
由 Jan "yenda" Trmal 提交于
* Github action for kaldi * add ccache * remove spaces
-
- 12 8月, 2022 2 次提交
-
-
由 Jan "yenda" Trmal 提交于
* Kaldi recipe for SPGISpeech * adding readme to spgispeech * fixing some style issues * more syntax checks cleared * more style fixes * yaml format fix * fix issues reported by @desh2608 * remove the conda calls * remove more shellcheck errors * fix one more grumpy shellcheck
-
由 Jan "yenda" Trmal 提交于
fixed portaudio archive location fixed case when the directory portaudio exists fixed whitespace formatting
-
- 20 7月, 2022 1 次提交
-
-
由 Christoph Boeddeker 提交于
-
- 15 7月, 2022 2 次提交
-
-
由 Christoph Boeddeker 提交于
-
由 Christoph Boeddeker 提交于
-
- 25 6月, 2022 1 次提交
-
-
由 Zohan 提交于
* Fix build for Windows * Remove double cctype
-