README.md 709 字节
Newer Older
H
Hui Zhang 已提交
1 2
# Examples for SpeechX

H
Hui Zhang 已提交
3
* `ds2_ol` - ds2 streaming test under `aishell-1` test dataset. 
H
Hui Zhang 已提交
4

H
Hui Zhang 已提交
5
## How to run  
H
Hui Zhang 已提交
6 7 8

`run.sh` is the entry point.

H
Hui Zhang 已提交
9
Example to play `ds2_ol`:
H
Hui Zhang 已提交
10 11

```
H
Hui Zhang 已提交
12
pushd ds2_ol/aishell
H
Hui Zhang 已提交
13
bash run.sh
H
format  
Hui Zhang 已提交
14
```
H
Hui Zhang 已提交
15

H
Hui Zhang 已提交
16
## Display Model with [Netron](https://github.com/lutzroeder/netron)  
H
Hui Zhang 已提交
17 18 19 20 21

```
pip install netron
netron exp/deepspeech2_online/checkpoints/avg_1.jit.pdmodel  --port 8022 --host 10.21.55.20
```
H
Hui Zhang 已提交
22

H
Hui Zhang 已提交
23 24 25 26 27 28
## For Developer  

> Warning: Only for developer, make sure you know what's it.

* dev - for speechx developer, using for test.

H
Hui Zhang 已提交
29 30
## Build WFST  

H
Hui Zhang 已提交
31 32
> Warning: Using below example when you know what's it.

H
Hui Zhang 已提交
33 34 35
* text_lm - process text for build lm
* ngram - using to build NGram ARPA lm.
* wfst - build wfst for TLG.