flowtron
hifi-gan
| flowtron | hifi-gan | |
|---|---|---|
| 6 | 5 | |
| 881 | 1,764 | |
| 0.3% | - | |
| 0.0 | 0.0 | |
| 10 months ago | 10 months ago | |
| Jupyter Notebook | Python | |
| Apache License 2.0 | 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.
flowtron
- [D] What is the best open source text to speech model?
- A thought: we need language and voice synthesis models as free as Stable Diffusion
-
Ask HN: Best FOSS software to read text allowed
If you want free (as open source) software, the NVIDIA research GitHub also has some good tools. For example : https://github.com/NVIDIA/flowtron
-
Visas Marr on the tragedy of Darth Plagueis
Voice in this video was synthesized using a Flowtron trained on Visas' speech patterns.(https://github.com/NVIDIA/flowtron)
-
Bastila Shan reads the Sith and Jedi Codes
The voicelines in this video was created using a Flowtron Text-to-Speech (TTS) model trained on Bastila's voice patterns to read the Sith and Jedi Codes. For more information: https://github.com/NVIDIA/flowtron I created a small tutorial for how to use it on Google Colab: https://www.youtube.com/watch?v=1Bmg1c5U5Bg
-
I created a Text-to-Speech model based on Bastila's voice patterns.
For more information on Flowtron: https://github.com/NVIDIA/flowtron/
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.)
What are some alternatives?
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)
WaveRNN - WaveRNN Vocoder + TTS
tacotron - A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
wavegrad - A fast, high-quality neural vocoder.
espnet - End-to-End Speech Processing Toolkit
Parallel-Tacotron2 - PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
diffwave - DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
espeak-ng - eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)