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.

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

Go to file

yangyaming f49eab5fec Change assert to exception raising.		7 years ago
data	Update DS2 README.md and fix bug in librispeech.py	7 years ago
README.md	Update DS2 README.md and fix bug in librispeech.py	7 years ago
audio_data_utils.py	1. Fix incorrect decoder result printing.	7 years ago
decoder.py	Refactor decoder interfaces and add ./data directory.	7 years ago
infer.py	Refactor decoder interfaces and add ./data directory.	7 years ago
model.py	Refactor decoder interfaces and add ./data directory.	7 years ago
requirements.txt	1. Fix incorrect decoder result printing.	7 years ago
train.py	Change assert to exception raising.	7 years ago

README.md

Deep Speech 2 on PaddlePaddle

Installation

Please replace $PADDLE_INSTALL_DIR with your own paddle installation directory.

pip install -r requirements.txt
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 data
python librispeech.py
cd ..

More help for arguments:

python librispeech.py --help

Traininig

For GPU Training:

CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --trainer_count 4

For CPU Training:

python train.py --trainer_count 8 --use_gpu False

More help for arguments:

python train.py --help

Inferencing

python infer.py

More help for arguments:

python infer.py --help