tacotron

that is interesting! can you describe how that transcription process works? if i have an audiobook and the corresponding ebook/pdf, isn't that already transcribed? or does transcription here mean something else? i'd also be happy to use an existing voice (the english one from keith ito sounds pleasant enough) but i am confused how to use it to read a book. there is code for a model that learns to synthesize speech from the data: https://github.com/keithito/tacotron but i don't see how to get at the end result which i think would hopefully also be available somewhere so i can just use it to read something.

https://github.com/NVIDIA/tacotron2 https://github.com/keithito/tacotron https://github.com/NVIDIA/WaveGlow

Maybe interesting: https://colab.research.google.com/drive/1SPl226SwzrfMZltrVag... https://github.com/keithito/tacotron https://www.youtube.com/watch?v=ijhZR43TOwc https://heartbeat.fritz.ai/a-2019-guide-to-speech-synthesis-...

Worth noting that a big chunk of the core TTS code here is built on tools from other researchers like Ryuichi Yamamoto and Keith Ito, and they have great implementations to check out as well. The best quality I have heard in OSS is probably [1] from Ryuichi using the Tacotron 2 implementation of Rayhane Mamah, which is loosely what NVidia based some of their baseline code on recently as well [3][4]. There's also a colab notebook for this stuff, so you can try it directly without any pain https://colab.research.google.com/github/r9y9/Colaboratory/b... I also have my own pipeline for this (using some utilities from the above authors + a lot of my own hacks), for a forthcoming paper release here https://github.com/kastnerkyle/representation_mixing/tree/ma... , see the minimal demo. It has pretty fast sampling, but the audio quality is not a

Thank you so much for this link, that is the best text-to-speech with an open architecture I've ever heard 'til now. Under https://github.com/keithito/tacotron you can find a pre-trained model based on this paper, although it isn't matching the quality yet. Maybe I can get some cluster time to train a new model using multiple datasets. Edit: Another interesting one: http://research.baidu.com/deep-voice-3-2000-speaker-neural-t...