TensorFlowTTS
hifi-gan
TensorFlowTTS | hifi-gan | |
---|---|---|
6 | 5 | |
3,702 | 1,764 | |
0.9% | - | |
0.0 | 0.0 | |
5 months ago | 10 months ago | |
Python | 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.
TensorFlowTTS
-
Ask HN: On-Device Text to Speech
Hey HN, has anyone found a viable solution for doing this locally and offline on iOS? I'd like to offer a privacy-friendly text to speech feature to my App, and Apple's speech synthesis sounds awful compared to some newer models and TTS engines. The only thing I've found is an older TensorflowTTS example here: https://github.com/TensorSpeech/TensorFlowTTS/tree/master/examples/ios
Any pointers or tips appreciated.
-
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
I had a lot of success using [FastSpeech2 + MB MelGAN via TensorFlowTTS](https://github.com/TensorSpeech/TensorFlowTTS). There are demos for [iOS](https://github.com/TensorSpeech/TensorFlowTTS/tree/master/ex...) and [Android](https://github.com/TensorSpeech/TensorFlowTTS/tree/master/ex...) which will allow you to run pretty convincing, modern TTS models with only a few hundred milliseconds of processing latency.
-
TTS mobile help
I need an example of how I would go about it. I've combed through examples but it's just not clicking for me.
-
A Working TTS feature has been found (No Google Services Required)
https://github.com/TensorSpeech/TensorFlowTTS was the project. It was pretty much a direct compile and run. I went through and added the required features to enable it as TTS service for Android. I also moved the Tensorflow portion into a separate thread from the TTS service directly, since Android restricts it's TTS service to a single thread, and the Tensorflow service uses five threads to run at a good speed. It's a much much heavier solution than a C/C++ compiled library, but it works out of the box and I will worry about optimizations later
-
Free library for text-to-speech
You need to try, it implements most advanced algorithms and not as ad-hoc as nvidia https://github.com/TensorSpeech/TensorFlowTTS
-
Reviving the 1973 Unix text to voice translator
For open source offline TTS with more or less recent algorithms you can check
https://github.com/TensorSpeech/TensorFlowTTS
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?
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
WaveRNN - WaveRNN Vocoder + TTS
TTS - :robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
wavegrad - A fast, high-quality neural vocoder.
TTS - πΈπ¬ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
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.
FairMOT - [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
Lip2Speech - A pipeline to read lips and generate speech for the read content, i.e Lip to Speech Synthesis.
mlp-singer - Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis (IEEE MLSP 2021)