lyra
descript-audio-codec
Our great sponsors
lyra | descript-audio-codec | |
---|---|---|
18 | 2 | |
3,720 | 847 | |
0.9% | - | |
0.0 | 4.5 | |
over 1 year ago | about 1 month ago | |
C++ | 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.
lyra
-
TSAC: Low Bitrate Audio Compression
Since Ballard's codec is "AI" based, can you add google's lyrav2 ( https://github.com/google/lyra ) and Facebook's/meta EnCodec ( https://github.com/facebookresearch/encodec ).
Also I don't seem to be able to access your page, so there might be error.
Finally, when doing opus comparison it's good now to denote if it is using Lace or NoLace decoder post processing filters that became available in opus 1.5 (note, this feature need to be enabled at compile time, and defying decode a new API call needs to be made to force higher complexity decoder) . See https://opus-codec.org/demo/opus-1.5/
-
Opus Databending Drumkit
I've thought about doing something similar for google's voice compression lyra https://github.com/google/lyra
-
Is it safe to say AV1 for video and OPUS for audio are best codecs respectively?
edit: It seems Lyra is opensource https://github.com/google/lyra
-
New Release of Audio Codec "Lyra" 1.3 (43% smaller and 20% faster)
1) https://github.com/google/lyra/releases/tag/v1.3.0
- Release Lyra 1.3.0 · google/lyra - performing arithmetic operations in 8-bit integers instead of 32-bit floats, the new model is 43% smaller (TFLite model size) and 20% faster
- Using AI to compress audio files for quick and easy sharing
-
Lyra V2 – a better, faster, and more versatile speech codec
Very impressive.
It'd be interesting to see what the lift would be to get encoding & decoding running in webassembly/wasm. Further, it'd be really neat to try to take something like the tflife_model_wrapper[1] and to get it backed by something like tsjs-tflite[2] perhaps even atop for example tfjs-backend-webgpu[3].
Longer run, the web-nn[4] spec should hopefully simplify/bake-in some of these libraries to the web platform, make running inference much easier. But there's still an interesting challenge & question, that I'm not sure how to tackle; how to take native code, compile it to wasm, but to have some of the implementation provided else-where.
[1] https://github.com/google/lyra/pull/89/files#diff-ed2f131a63...
[2] https://www.npmjs.com/package/@tensorflow/tfjs-tflite
[3] https://www.npmjs.com/package/@tensorflow/tfjs-backend-webgp...
[4] https://www.w3.org/TR/webnn/
-
Lyra 1.2.0 released with 5x speed improvement, higher quality speech, selectable bitrate (3.2, 6.0 and 9.2 kb/s), lower latency and Mac and Windows support
You can find an Android, Linux and macOS app here: https://github.com/google/lyra/actions/runs/3156735950
-
(Noob): Can Signal implement Lyra-Codec (developed by Google) for better audio quality?
Here's the repository: https://github.com/google/lyra and it's licensed under Apache.
- Lyra 0.0.2 ·The main improvement is the open-source release of the sparse_matmul library code, which was co-developed by Google and DeepMind. no more pre-compiled .so dynamic library binaries and no more restrictions on which toolchain to use, which opens up the door to port onto different platforms
descript-audio-codec
-
Show HN: Sonauto – a more controllable AI music creator
Hey HN,
My cofounder (four months ago, classmate) and I trained an AI music generation model and after a month of testing we're launching 1.0 today. Ours is interesting because it's a latent diffusion model instead of a language model, which makes it more controllable: https://sonauto.ai/
Others do music generation by training a Vector Quantized Variational Autoencoder like Descript Audio Codec (https://github.com/descriptinc/descript-audio-codec) to turn music into tokens, then training an LLM on those tokens. Instead, we ripped the tokenization part off and replaced it with a normal variational autoencoder bottleneck (along with some other important changes to enable insane compression ratios). This gave us a nice, normally distributed latent space on which to train a diffusion transformer (like Sora). Our diffusion model is also particularly interesting because it is the first audio diffusion model to generate coherent lyrics!
We like diffusion models for music generation because they have some interesting properties that make controlling them easier (so you can make your own music instead of just taking what the machine gives you). For example, we have a rhythm control mode where you can upload your own percussion line or set a BPM. Very soon you'll also be able to generate proper variations of an uploaded or previously generated song (e.g., you could even sing into Voice Memos for a minute and upload that!). @Musicians of HN, try uploading your songs and using Rhythm Control/let us know what you think! Our goal is to enable more of you, not replace you.
For example, we turned this drum line (https://sonauto.ai/songs/uoTKycBghUBv7wA2YfNz) into this full song (https://sonauto.ai/songs/KSK7WM1PJuz1euhq6lS7 skip to 1:05 if inpatient) or this other song I like better (https://sonauto.ai/songs/qkn3KYv0ICT9kjWTmins we accidentally compressed it with AAC instead of Opus which hurt quality, though)
We also like diffusion models because while they're expensive to train, they're cheap to serve. We built our own efficient inference infrastructure instead of using those expensive inference as a service startups that are all the rage. That's why we're making generations on our site FREE and UNLIMITED for as long as possible.
We'd love to answer your questions. Let us know what you think of our first model! https://sonauto.ai/
-
TSAC: Low Bitrate Audio Compression
Another useful model to compare to would be DAC https://github.com/descriptinc/descript-audio-codec
This is the codec that TSAC extended, so it could be a nice comparison to see. I'd also echo Vocos (from sibling comment), it operates on the same Encodec tokens but generally has better reconstruction quality.
What are some alternatives?
codec2 - Open source speech codec designed for communications quality speech between 700 and 3200 bit/s. The main application is low bandwidth HF/VHF digital radio.
ESP32_Codec2 - Codec2 library for ESP32 (Arduino)
minisearch - Tiny and powerful JavaScript full-text search engine for browser and Node
Bazel - a fast, scalable, multi-language and extensible build system
elasticsearch-py - Official Python client for Elasticsearch
regex-benchmark - It's just a simple regex benchmark of different programming languages.
signal-ringrtc-node
jukebox - Code for the paper "Jukebox: A Generative Model for Music"
mpc-hc - Media Player Classic