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 '830e91ca5c'
${ noResults }
PaddleSpeech/examples/other/g2p
History
TianYuan d50d195145
update frontend readme, test=doc 		3 years ago
..
README.md update frontend readme, test=doc 3 years ago
get_g2p_data.py [asr] logfbank with dither (#1179) 3 years ago
path.sh [TTS]fix praatio version, test=tts (#1158) 3 years ago
run.sh change nprocs to ngpu, add aishell3/voc1 3 years ago
test_g2p.py change nprocs to ngpu, add aishell3/voc1 3 years ago

README.md

G2P

For g2p, we use BZNSYP's phone label as the ground truth and we delete silence tokens in labels and predicted phones.

You should Download BZNSYP from its Official Website and extract it. Assume the path to the dataset is ~/datasets/BZNSYP.

We use WER as an evaluation criterion.

Start

Run the command below to get the results of the test.

./run.sh

The avg WER of g2p is: 0.027124048652822204

     ,--------------------------------------------------------------------.
     |        | # Snt    # Wrd  | Corr    Sub    Del    Ins    Err  S.Err |
     |--------+-----------------+-----------------------------------------|
     | Sum/Avg|  9996   299181  | 97.3    2.7    0.0    0.0    2.7   52.2 |
     `--------------------------------------------------------------------'