GST-Tacotron
GST-Tacotron copied to clipboard
A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Bumps [ujson](https://github.com/ultrajson/ultrajson) from 1.35 to 5.4.0. Release notes Sourced from ujson's releases. 5.4.0 Added Add support for arbitrary size integers (#548) @JustAnotherArchivist Fixed CVE-2022-31116: Replace wchar_t string decoding implementation with...
Bumps [numpy](https://github.com/numpy/numpy) from 1.14.3 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
Hi. I am exploring about speed of training and inference different multi speaker TTS models on single CPU or singe GPU. Thanks for any explanation in this case for current...
Can I get to the pre-trained weight of blizzard?
@KinglittleQ 你好,受限感谢分享的卓越工作,受益匪浅。  有个问题请教,这里 shift 的作用是什么呢?
How do we ensure that the padding of the reference mel spectogram is taken into account when the reference encoder is applied on a batch of mels?
Bumps [joblib](https://github.com/joblib/joblib) from 0.11 to 1.2.0. Changelog Sourced from joblib's changelog. Release 1.2.0 Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported....
as the picture depicted, the attention is broken. and when I use this model to generate wavs, is generate silence audio. why ?????
Start loading data /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0259.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0260.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0261.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0262.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0263.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0264.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0265.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0266.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0267.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0268.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0269.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0270.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0271.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0272.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0273.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0274.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0275.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0276.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0277.wav /home/zhonghuihang/data/LJSpeech-1.1/wavs/LJ050-0278.wav Finish loading data Traceback (most recent call...
Bumps [certifi](https://github.com/certifi/python-certifi) from 2018.4.16 to 2022.12.7. Commits 9e9e840 2022.12.07 b81bdb2 2022.09.24 939a28f 2022.09.14 aca828a 2022.06.15.2 de0eae1 Only use importlib.resources's new files() / Traversable API on Python ≥3.11 ... b8eb5e9 2022.06.15.1...