Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
| Date | Stars |
|---|---|
| 2026-07-31 | 2624 |
| 2026-08-03 | 2624 |
| 2026-08-06 | 2626 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<img src="./audiolm.png" width="600px"></img> ## AudioLM - Pytorch Implementation of <a href="https://google-research.github.io/seanet/audiolm/examples/">AudioLM</a>, a Language Modeling Approach to Audio Generation out of Google Research, in Pytorch It also extends the work for conditioning with classifier free guidance with T5. This allows for one to do text-to-audio or TTS, not offered in the paper. Yes, this means <a href="https://valle-demo.github.io/">VALL-E</a> can be trained from this repository. It is essentially the same. Please join <a href="https://discord.gg/xBPBXfcFHd"><img alt="Join us on Discord" src="https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white"></a> if you are interested in replicating this work in the open This repository now also contains a MIT licensed version of <a href="https://arxiv.org/abs/2107.03312">SoundStream</a>. It is also compatible with <a href="https://github.com/facebookresearch/encodec">EnCodec</a>, which is also [MIT-licensed](https://github.com/facebookresearch/encodec/commit/349b72939f57cb3bc7b60906c0ee8228c849485d) at the time of writing. Update: AudioLM was essentially used to 'solve' music generation in the new <a href="https://github.com/lucidrains/musiclm-pytorch">MusicLM</a> In the future, <a href="https://www.youtube.com/watch?v=olNvmUCmY8o">this movie clip</a> would no longer make any sense. You would just prompt an AI instead. ## Appreciation - <a href="https://stability.ai/">Stability.ai</a> for the generous sponsorship to work and open source cutting edge artificial intelligence research - <a href="https://huggingface.co/">🤗 Huggingface</a> for their amazing accelerate and transformers libraries - <a href="https://ai.facebook.com/">MetaAI</a> for <a href="https://github.com/facebookresearch/fairseq">Fairseq</a> and the liberal license - <a href="https://github.com/eonglints">@eonglints</a> and <a href="https://github.com/turian">Joseph</a> for offering their professional advice and expertise as well as pull requests! - <a href="https://github.com/djqualia">@djqualia</a>, <a href="https://github.com/yigityu">@yigityu</a>, <a href="https://github.com/inspirit">@inspirit</a>, and <a href="https://github.com/BlackFox1197">@BlackFox1197</a> for helping with the debugging of soundstream - <a href="https://github.com/zhvng">Allen</a> and <a href="https://github.com/LWprogramming">LWprogramming</a> for reviewing the code and submitting bug fixes! - <a href="https://github.com/ilya16">Ilya</a> for finding an issue with multi-scale discriminator downsampling and for soundstream trainer improvements - <a href="https://github.com/AndreyBocharnikov">Andrey</a> for identifying a missing loss in soundstream and guiding me through the proper mel spectrogram hyperparameters - <a href="https://github.com/alexdemartos">Alejandro</a> and <a href="https://github.com/ilya16">Ilya</a> for sharing their results with training soundstream, and for working through a few issues with the local attention positional embeddings - <a href="https://github.com/LWprogramming">LWprogramming</a> for adding Encodec compatibility! - <a href="https://github.com/LWprogramming">LWprogramming</a> for finding an issue with handling of the EOS token when sampling from the `FineTransformer`! - <a href="https://github.com/YoungloLee">@YoungloLee</a> for identifying a big bug in the 1d causal convolution for soundstream related to padding not accounting for strides! - <a href="https://github.com/haydenshively">Hayden</a> for pointing out some discrepancies in the multi-scale discriminator for Soundstream ## Install ```bash $ pip install audiolm-pytorch ``` ## Usage ### SoundStream & Encodec There are two options for the neural codec. If you want to use the pretrained 24kHz Encodec, just create an Encodec object as follows: ```python from audiolm_pytorch import EncodecWrapper encodec = EncodecWrapper() # Now you can use the encodec variable in the same w
Excerpt of 22,437 characters
Read on GitHub
Phil Wang · United States
473
36
8
6
Ilya Borovik
5
5
4
4
2
Hayk Martiros · Skydio · United States
2
1
Dom
1
1
1
1
1
1
Eren Gölge · Cantina.ai
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:08e4e2e5fd8048a8, topic:deep-learning