hifi-gan
WaveRNN
hifi-gan | WaveRNN | |
---|---|---|
5 | 5 | |
1,764 | 2,086 | |
- | - | |
0.0 | 0.0 | |
9 months ago | almost 2 years ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hifi-gan
- [D] What is the best open source text to speech model?
- I made Lisa-nee TTS (Imai Lisa)
- HiFi-GAN: Generative Adversarial Networks for Efficient and Hi-Fi Speech Synth
-
[2108.13320] Neural HMMs are all you need (for high-quality attention-free TTS)
It will be interesting to see if the artefacts you noticed persist once we've trained the model for longer and switch to a better vocoder such as HiFi-GAN. (The paper and audio examples use WaveGlow since that's the default of the repository we compared ourselves to.) That said, "choppiness" sounds to me like it might be related to the temporal evolution, in which case it's something that a non-causal, convolutional post-net might be able to smooth over.
-
The dangers of AI
Hey, as far as I know this paper is the current SoTA on public data that is open source. Github is here. If you are interested in really getting into speech synthesis, this page has everything (modern stuff on the bottom.)
WaveRNN
- Ich werde bald, vorrausichtlich noch dieses Jahr, stumm werden. Was nun?
-
Eminem Disses Forsen
I've posted before, but its this open source https://github.com/fatchord/WaveRNN with a very basic gui and a connection to the streamlabs socket api which sends out json of the dono. The actual app forsen has is probably a day of work.
-
Johnny Silverhand TTS. Some classic lines
Its not enough. You need at least 8GB VRAM for GPU training. My specs are 3700x + 2080s, CPU training is <1step/sec and GPU is up to 5steps/sec. Even with this GPU I have "out of memory" erros sometimes (hint: if someone else wants to try wavernn check my pull request to reduce gpu memory usage). You can use online services to train your data like Google Colab but it might be too expensive for you.
-
Weekly Noobquestions Thread December 29 2020
I may have found an a program that works. Its the same algorithm that the streamer forsen uses for his TTS, and it can emulate his own voice(which has a swedish accent) or voices of other notable people with accents. It appears like it has the ability to give it your own data set so I'll see if I can get it to work. For anyone finding the post this is the link: https://github.com/fatchord/WaveRNN
What are some alternatives?
wavegrad - A fast, high-quality neural vocoder.
Parallel-Tacotron2 - PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
flowtron - Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer
diffwave - DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
TTS - πΈπ¬ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
TensorFlowTTS - :stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
mlp-singer - Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis (IEEE MLSP 2021)
vall-e - An unofficial PyTorch implementation of the audio LM VALL-E