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 '7eb8fa72a1'
${ noResults }
PaddleSpeech/examples/voxceleb
History
xiongxinlei 7eb8fa72a1
convert save_freq to save_interval, test=doc 		3 years ago
..
sv0 convert save_freq to save_interval, test=doc 3 years ago
README.md add vox2 data into VoxCeleb class 3 years ago

README.md

dataset info refer to VoxCeleb

sv0 - speaker verfication with softmax backend etc, all python code more info refer to the sv0/readme.txt

sv1 - dependence on kaldi, speaker verfication with plda/sc backend, more info refer to the sv1/readme.txt

VoxCeleb2 preparation

VoxCeleb2 audio files are released in m4a format. All the VoxCeleb2 m4a audio files must be converted in wav files before feeding them in PaddleSpeech. Please, follow these steps to prepare the dataset correctly:

  1. Download Voxceleb2. You can find download instructions here: http://www.robots.ox.ac.uk/~vgg/data/voxceleb/

  2. Convert .m4a to wav VoxCeleb2 stores files with the m4a audio format. To use them in PaddleSpeech, you have to convert all the m4a audio files into wav files.

ffmpeg -y -i %s -ac 1 -vn -acodec pcm_s16le -ar 16000 %s

You can do the conversion using ffmpeg https://gist.github.com/seungwonpark/4f273739beef2691cd53b5c39629d830). This operation might take several hours and should be only once.

  1. Put all the wav files in a folder called wav. You should have something like voxceleb2/wav/id*/*.wav (e.g, voxceleb2/wav/id00012/21Uxsk56VDQ/00001.wav)