-
*Build commands:*
```console
git clone https://github.com/k2-fsa/sherpa-onnx
cd sherpa-onnx
cmake -B build .
cmake --build build -j8
```
**Note:** the error disapper if I add `-DCMAKE_BUILD…
-
Hi,
Thanks for sharing.
Do you not need to subtract mean from the input video frames for training the model using VGG 16 layer model as initial weights? I have not seen that part in your implement…
-
Below are the execution commands and console output results for my entire training process.
(rvt) pe@505-1-ubuntu20-04-5-lts:~/projects/yxl/RVT/RVT-master$ DATA_DIR=/home/pe/projects/yxl/gen1
(rvt…
-
You May Not Need Attention. 2018
Ofir Press, Noah A. Smith
https://arxiv.org/abs/1810.13409
https://github.com/ofirpress/YouMayNotNeedAttention
## 概要
NMT (Neural Machine Translation)において，アテ…
-
**Submitting author:** @timothyas (Timothy Smith)
**Repository:** https://github.com/timothyas/xesn
**Branch with paper.md** (empty if default branch):
**Version:** v0.1.4
**Editor:** @sneakers-the-r…
-
ICU's BreakIterator has clear limitations in its approach for character-based languages without textual word boundaries. When used directly, it allows you to specify a dictionary to work around limita…
-
Post a link for a "possibility" reading of your own on the topic of Sound and Image Learning [for week 7], accompanied by a 300-400 word reflection that: 1) briefly summarizes the article (e.g., as we…
lkcao updated
2 years ago
-
Hello,
Thank you for the awesome work. While going through the paper, I found that in Table 1, there seems to be a typo in the following statement "Entries in gray are trained trained for 400 epoc…
-
I finetuned the Arabic model on my dataset :
and this is my config file:
```
numbe…
-
I created a confomer-rnn-trasducer recipe using CSJ and run the training process.
When I evaluated the created model, the CERs for eval1, eval2, and eval3 were higher than the [original paper](https:…