{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/6"}],"enrichment":{"capability":"SNAC compresses audio into discrete hierarchical tokens at low bitrate, enabling efficient audio representation for neural codecs and language modeling approaches to audio generation.","skillfed_tags":["audio-codec","neural-compression","tokenization"],"use_cases":["Compress speech or music into discrete tokens for downstream language model training on audio.","Reduce audio bitrate for storage or transmission while preserving perceptual quality.","Generate audio using discrete token sequences in a language modeling framework.","Reconstruct audio from encoded tokens for real-time or batch audio processing pipelines."],"what_it_does":"SNAC is a neural audio codec that encodes audio into hierarchical discrete tokens at low bitrate. It follows the architecture of SoundStream, EnCodec, and DAC but uses coarse tokens sampled at lower frequency to cover broader time spans, reducing bitrate while enabling long-context audio modeling\u2014for example, 2048 coarse tokens at ~10 Hz can represent ~3 minutes of audio structure.\n\nThe package provides pretrained models for speech (24 kHz, 0.98 kbps) and music/sound effects (32 kHz and 44 kHz, 1.9\u20132.6 kbps). It depends on torch, numpy, einops, and huggingface-hub to load models. Encoding and decoding are straightforward: load a model, call encode() on audio tensors, and retrieve a list of token sequences at different resolutions.","worth_installing":"Yes, if you need neural audio compression for language modeling or token-based audio generation and can work with mono audio on GPU. The low install friction and established model zoo make it straightforward to integrate. However, verify the license before production use, and note that maintenance is dormant\u2014expect no active updates, though the package is stable and has no known vulnerabilities."},"id":"snac","links":{"html":"https://skillfed.io/packages/snac","md":"https://skillfed.io/packages/snac.md","pypi":"https://pypi.org/project/snac/"},"maintenance":{"status":"dormant"},"meta":{"latest_release":"2024-09-11","license_spdx":null,"license_treatment":"unclear","name":"snac","python_support":"unspecified","summary":"Multi-Scale Neural Audio Codec"},"popularity":{"monthly_downloads":272475,"position":8209,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"1.2.1"}