msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '79879451fb'
${ noResults }
PaddleSpeech/speechx/examples
History
Hui Zhang 8271fcfb0a
fix as comment 		2 years ago
..
codelab fix as comment 2 years ago
custom_asr remove streaming opt, test=doc 2 years ago
ds2_ol refactor ctc opts, extract decoder interface, add ctc beamsearch score 2 years ago
text_lm format 2 years ago
u2pp_ol more log 2 years ago
.gitignore fix speech egs 2 years ago
README.md fix cmake paddle flags; more doc info 2 years ago

README.md

Examples for SpeechX

u2pp_ol is recommended.

  • u2pp_ol - u2++ streaming asr test under aishell-1 test dataset.
  • ds2_ol - ds2 streaming test under aishell-1 test dataset.

How to run

Create env

Using tools/evn.sh under speechx to create python env.

bash tools/env.sh

Source env before play with example.

. venv/bin/activate

Play with example

run.sh is the entry point for every example.

Example to play u2pp_ol:

pushd u2pp_ol/wenetspeech
bash run.sh --stop_stage 4

Display Model with Netron

If you have a model, we can using this commnd to show model graph.

For example:

pip install netron
netron exp/deepspeech2_online/checkpoints/avg_1.jit.pdmodel  --port 8022 --host 10.21.55.20

For Developer

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

  • codelab - for speechx developer, using for test.