FastSpeech2
hifi-gan
| FastSpeech2 | hifi-gan | |
|---|---|---|
| 4 | 5 | |
| 1,612 | 1,764 | |
| - | - | |
| 0.0 | 0.0 | |
| 6 months ago | 9 months 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.
FastSpeech2
-
[D] What is the best open source text to speech model?
FastSpeech2 submitted: Jun 8, 2020 paper: https://arxiv.org/pdf/2006.04558.pdf github: https://github.com/ming024/FastSpeech2 (Not the official implementation but is the once cited the most)
-
What voice-changing apps are available right now?
We have the TorToiSe repo, the SV2TTS repo, and from here you have the other models like Tacotron 2, FastSpeech 2, and such. A there is a lot that goes into training a baseline for these models on the LJSpeech and LibriTTS datasets. Fine tuning is left up to the user.
- I'm looking for something self-hosted, preferably linux-based (though win or mac will work too), that will allow me to train a 'voice model' with pre-recorded speech, and then replicate it from text of my choice.
-
Voice-cloning library for conlangs?
As for synthesis of text using your own voice - you can dig into Real Time Voice Cloning or maybe FastSpeech2, but I am not sure if you can use it with conlangs (and because of ML nature, you need many, many, many training data to get anything interesting).
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?
Parallel-Tacotron2 - PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
WaveRNN - WaveRNN Vocoder + TTS
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
wavegrad - A fast, high-quality neural vocoder.
tacotron2 - Tacotron 2 - PyTorch implementation with faster-than-realtime inference
voice100 - Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without autoregression.
diffwave - DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
tacotron - A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
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)