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

Xinghai Sun 9c3cd3c704 Update some parameters and comments.		7 years ago
README.md	Add infererence and add SortaGrad for only first pass.	7 years ago
audio_data_utils.py	Add function docs.	7 years ago
eng_vocab.txt	Add librispeech dataset, audio data provider and simplfied DeepSpeech2 model configuration.	7 years ago
infer.py	Add function docs.	7 years ago
librispeech.py	Add function docs.	7 years ago
model.py	Add function docs.	7 years ago
requirements.sh	Add infererence and add SortaGrad for only first pass.	7 years ago
train.py	Update some parameters and comments.	7 years ago

README.md

Deep Speech 2 on PaddlePaddle

sh requirements.sh
python librispeech.py
python train.py

Please add warp-ctc library path (usually $PADDLE_INSTALL_DIR/Paddle/third_party/install/warpctc/lib) to LD_LIBRARY_PATH.