lyra
encodec
Our great sponsors
| lyra | encodec | |
|---|---|---|
| 18 | 18 | |
| 3,720 | 3,172 | |
| 0.9% | 3.7% | |
| 0.0 | 3.9 | |
| over 1 year ago | 4 months 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
encodec
-
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/
-
[R] Neural network for audio training sample size
But models rarely work on raw audio. You can also check EnCodec (https://github.com/facebookresearch/encodec) or SoundStream.
- Bark: A transformer based text to audio system
-
[D]: Is voice cloning or natural TTS (like Elevenlabs) possible due to LLMs?
VALL-E from Microsoft is transformer over Encodec code. SPEAR-TTS from Google is basically AudioLM for TTS.
- Why hasn't Meta made LLaMA open source?
- ML Codecs Similar to Encodec by Facebook?
- Wie Österreich die Glasfaser verschlief - ORF Topos
- EnCodec: State-of-the-art deep learning based audio codec
- High Fidelity Neural Audio Compression
- EnCodec: High Fidelity Neural Audio Compression
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.
bark - 🚀 BARK INFINITY GUI CMD 🎶 Powered Up Bark Text-prompted Generative Audio Model
ESP32_Codec2 - Codec2 library for ESP32 (Arduino)
bark - 🔊 Text-Prompted Generative Audio Model
minisearch - Tiny and powerful JavaScript full-text search engine for browser and Node
bark-with-voice-clone - 🔊 Text-prompted Generative Audio Model - With the ability to clone voices
Bazel - a fast, scalable, multi-language and extensible build system
audiolm-pytorch - Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
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"