Commit f45db7b2 authored by Ho Yin Chan's avatar Ho Yin Chan
Browse files

trunk:src/doc minor update on documentation

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2976 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8
parent 59472733
......@@ -42,7 +42,7 @@ namespace kaldi {
predict the long-term future, but in the immediate future our aim is to both have
the freedom to work on our respective codebases, and to borrow ideas from each other.
In the example directories such as egs/wsj/s5/, egs/rm/s5 and egs/swbd/s5, neural
In the example directories such as egs/wsj/s5/, egs/rm/s5, egs/swbd/s5 and egs/hkust/s5b, neural
net example scripts can be found. Karel's example scripts can be found in local/run_dnn.sh
or local/run_nnet.sh, and Dan's example scripts can be found in local/run_nnet_cpu.sh.
Before running those scripts, the first stages of ``run.sh'' in those directories must
......
......@@ -72,8 +72,8 @@
Current progress/activity:
- Deep neural nets and other neural-net approaches. Karel Vesely is the main one working on this.
Petr Motlicek has obtained a good-performing TANDEM setup with Kaldi, but it still depends on
external tools (STK and TNet) to get the features. We'll try to move this into the Kaldi neural-net
training setup.
external tools (STK and TNet) to get the features. Ricky Chan has recently obtianed good performance
using GPU based Kaldi neural-net training setup with CUDA 5.0.
- Multilingual SGMMs. Arnab Ghoshal has been doing some work on this, and will be helped by Petr Motlicek
and Milos Janda.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment