Easy-to-use Speech Toolkit including SOTA/Streaming ASR with punctuation, influential TTS with text frontend, Speaker Verification System and End-to-End Speech Simultaneous Translation.

kws streaming-asr speech-alignment tts conformer speech-translation voice-recognition sound-classification transformer asr speech-synthesis voice-cloning punctuation-restoration streaming-tts speech-recognition vocoder

Go to file

Yibing Liu fd102c2110 Merge branch 'develop' into ctc_decoder_deploy		7 years ago
data_utils	modify some detail of augmentor	7 years ago
datasets	Add shuffle type of instance_shuffle and batch_shuffle_clipped.	7 years ago
deploy	add initial files for deployment	7 years ago
tests	remove augmentor unittest	7 years ago
README.md	Improve audio featurizer and add shift augmentor.	7 years ago
compute_mean_std.py	Enable min_batch_num in train.py and update train info print.	7 years ago
decoder.py	Add shuffle type of instance_shuffle and batch_shuffle_clipped.	7 years ago
deploy.py	add deploy.py	7 years ago
error_rate.py	Follow comments.	7 years ago
infer.py	Improve audio featurizer and add shift augmentor.	7 years ago
model.py	Add function, class and module docs for data parts in DS2.	7 years ago
requirements.txt	resolve conflict with setup.sh	7 years ago
setup.sh	Merge pull request #127 from pkuyym/fix-soundfile	7 years ago
train.py	Improve audio featurizer and add shift augmentor.	7 years ago
utils.py	Add shuffle type of instance_shuffle and batch_shuffle_clipped.	7 years ago

README.md

Deep Speech 2 on PaddlePaddle

Installation

Please replace $PADDLE_INSTALL_DIR with your own paddle installation directory.

sh setup.sh
export LD_LIBRARY_PATH=$PADDLE_INSTALL_DIR/Paddle/third_party/install/warpctc/lib:$LD_LIBRARY_PATH

For some machines, we also need to install libsndfile1. Details to be added.

Usage

Preparing Data

cd datasets
sh run_all.sh
cd ..

sh run_all.sh prepares all ASR datasets (currently, only LibriSpeech available). After running, we have several summarization manifest files in json-format.

A manifest file summarizes a speech data set, with each line containing the meta data (i.e. audio filepath, transcript text, audio duration) of each audio file within the data set, in json format. Manifest file serves as an interface informing our system of where and what to read the speech samples.

More help for arguments:

python datasets/librispeech/librispeech.py --help

Preparing for Training

python compute_mean_std.py

python compute_mean_std.py computes mean and stdandard deviation for audio features, and save them to a file with a default name ./mean_std.npz. This file will be used in both training and inferencing.

More help for arguments:

python compute_mean_std.py --help

Training

For GPU Training:

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python train.py

For CPU Training:

python train.py --use_gpu False

More help for arguments:

python train.py --help

Inferencing

CUDA_VISIBLE_DEVICES=0 python infer.py

More help for arguments:

python infer.py --help