PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS, FastSpeech2/FastPitch, SpeedySpeech, WaveFlow and Parallel WaveGAN)
We add some features in v0.4.0, including:
Fix a config key error.
fix some bugs about multiprocess training.
Experiemnts conducted with LJSpeech dataset are extended, from separate ones for acoustic models and vocoders, to chained ones. Neural acoustic models with neural vocoders work togather to make a simpler TTS pipeline.
Since the acoustic configurations for training the acoustic model and the vocoder is the same, chaining them is seamless.
Parakeet aims to provide a flexible, efficient and state-of-the-art text-to-speech toolkit for the open-source community. It is built on PaddlePaddle Dynamic graph and includes many influential TTS models proposed by Baidu Research and other research groups. This is the first release of Parakeet.
In particular, it features the latest WaveFlow model proposed by Baidu Research.