mirror of
https://github.com/hanzoai/skills.git
synced 2026-11-21 09:33:35 +00:00
hanzoskills.com/llms.txt now opens with the install line, the API reference index and the company index, so an agent that lands on any one of the three can find the rest. robots.txt claimed 537 documents while llms.txt counts 920. The number is gone from robots.txt; llms.txt derives it. public/ is regenerated from scripts/site.py, which it had fallen behind: the copy-prompt menu and agent bar were in the generator and not in the committed pages. tests/site.mjs passes against the result. Co-authored-by: Hanzo Dev <[email protected]>
412 lines
23 KiB
HTML
412 lines
23 KiB
HTML
<!doctype html>
|
|
<html lang="en"><head>
|
|
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
|
|
<title>hanzo-mugen</title>
|
|
<meta name="color-scheme" content="dark">
|
|
<style>
|
|
/* Committed to one visual world: a dark instrument panel. No light variant —
|
|
the dot field and the hairline rules only read on black, and a naive
|
|
inversion would wash both out. Every colour is painted explicitly so the page
|
|
never borrows a host background. */
|
|
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
|
|
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
|
|
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
|
|
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
|
|
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
|
|
|
|
:root{
|
|
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
|
|
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
|
|
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
|
|
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
|
|
--font-zen-pixel-square:'Zen Pixel Square',monospace;
|
|
--mono:var(--font-zen-mono);
|
|
--sans:var(--font-zen-sans);
|
|
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
|
|
--r:999px; --r-soft:14px;
|
|
}
|
|
*{box-sizing:border-box}
|
|
html{-webkit-text-size-adjust:100%}
|
|
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
|
|
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
|
|
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
|
|
|
|
/* The dot field. A halftone made of one repeating radial-gradient, faded out
|
|
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
|
|
/* No overflow clip here: the dot field is inset to the box already, and a clip
|
|
would cut off the copy-prompt menu. */
|
|
.hero{position:relative;border-bottom:1px solid var(--line)}
|
|
.hero::before{content:"";position:absolute;inset:0;
|
|
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
|
|
background-size:7px 7px;
|
|
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
|
|
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
|
|
pointer-events:none}
|
|
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
|
|
|
|
nav{border-bottom:1px solid var(--line)}
|
|
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
|
|
justify-content:space-between;align-items:center;gap:1rem}
|
|
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
|
|
text-transform:uppercase;color:var(--ink);text-decoration:none;
|
|
display:inline-flex;align-items:center;gap:.6rem}
|
|
.brand i{font-style:normal;color:var(--faint)}
|
|
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
|
|
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
|
|
text-transform:uppercase;color:var(--soft);text-decoration:none}
|
|
nav a.up:hover{color:var(--ink)}
|
|
|
|
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
|
|
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
|
|
h1 em{font-style:normal;color:var(--faint)}
|
|
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
|
|
|
|
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
|
|
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
|
|
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
|
|
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
|
|
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
|
|
line-height:1.2;font-weight:400}
|
|
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
|
|
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
|
|
.btn.solid:hover{background:#d8d8d4}
|
|
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
|
|
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
|
|
|
|
/* Copy-prompt selector. Each row copies the prompt for its own target. */
|
|
.copy{position:relative;display:inline-flex}
|
|
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
|
|
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
|
|
padding:.4rem;display:flex;flex-direction:column;
|
|
box-shadow:0 12px 32px rgba(0,0,0,.75)}
|
|
.menu[hidden]{display:none}
|
|
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
|
|
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
|
|
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
|
|
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
|
|
white-space:nowrap}
|
|
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
|
|
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
|
|
.mi:hover .mark{color:var(--ink)}
|
|
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
|
|
letter-spacing:.1em;text-transform:uppercase}
|
|
|
|
/* Works-with bar: one scrolling row, name and mark per agent. */
|
|
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
|
|
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
|
|
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
|
|
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
|
|
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
|
|
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
|
|
display:flex;align-items:center}
|
|
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
|
|
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
|
|
-webkit-overflow-scrolling:touch;
|
|
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
|
|
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
|
|
.bar::-webkit-scrollbar{display:none}
|
|
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
|
|
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
|
|
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
|
|
text-decoration:none;background:var(--ground)}
|
|
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
|
|
.agent .mark{width:.95rem;height:.95rem}
|
|
|
|
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
|
|
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
|
|
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
|
|
p{margin:0 0 1rem;max-width:70ch}
|
|
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
|
|
li{margin:.22rem 0}
|
|
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
|
|
text-decoration-color:var(--line-hi)}
|
|
a:hover{text-decoration-color:var(--ink)}
|
|
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
|
|
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
|
|
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
|
|
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
|
|
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
|
|
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
|
|
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
|
|
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
|
|
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
|
|
display:block;overflow-x:auto}
|
|
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
|
|
|
|
.curl{display:block;background:var(--panel);border:1px solid var(--line);
|
|
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
|
|
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
|
|
white-space:pre;line-height:1.9}
|
|
.curl b{color:var(--ink);font-weight:400}
|
|
.curl i{font-style:normal;color:var(--faint)}
|
|
|
|
/* index */
|
|
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
|
|
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
|
|
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
|
|
#q:focus{outline:none;border-color:var(--soft)}
|
|
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
|
|
text-transform:uppercase;margin:0 0 2rem}
|
|
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
|
|
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
|
|
padding-bottom:.45rem}
|
|
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
|
|
border-radius:var(--r-soft);text-decoration:none}
|
|
.row:hover{background:#0a0a0a}
|
|
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
|
|
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
|
|
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
|
|
color:var(--faint);font-size:.85rem}
|
|
footer a{color:var(--soft)}
|
|
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
|
|
margin:0 0 2rem;font-size:.85rem}
|
|
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
|
|
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
|
|
border-bottom:1px solid var(--line);padding-bottom:.4rem}
|
|
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
|
|
.fmap a:hover{text-decoration:underline}
|
|
.fmap div{color:var(--faint);line-height:1.5}
|
|
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
|
|
|
|
@media (max-width:640px){
|
|
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
|
|
.btns{gap:.5rem}
|
|
.btn{padding:.75rem 1.15rem;font-size:.68rem}
|
|
.copy,.copy .btn{width:100%;justify-content:center}
|
|
.menu{left:0;right:0;min-width:0}
|
|
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
|
|
.strip b{border-right:0;padding-right:0}
|
|
.bar{width:100%}
|
|
}
|
|
</style>
|
|
<link rel="alternate" type="text/markdown" href="/hanzo-mugen.md">
|
|
|
|
<link rel="icon" href="/favicon.svg">
|
|
<link rel="canonical" href="https://hanzoskills.com/hanzo-mugen">
|
|
</head>
|
|
<!-- Reading this with a machine? Every page here is also plain markdown.
|
|
This one: https://hanzoskills.com/hanzo-mugen.md
|
|
Index: https://hanzoskills.com/llms.txt
|
|
Corpus: https://hanzoskills.com/all.md
|
|
Append .md to any path for the markdown twin. -->
|
|
<body>
|
|
<nav><div class="in">
|
|
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
|
|
<a class="up" href="/">All skills</a>
|
|
</div></nav>
|
|
|
|
<div class="wrap">
|
|
<h1>hanzo-mugen</h1><p class="lede">Mugen is a PyTorch framework for deep learning research on audio generation.</p><h1>Hanzo Mugen - Audio Generation Framework</h1>
|
|
<p><strong>Category</strong>: Hanzo Ecosystem <strong>Related Skills</strong>: <code>hanzo/hanzo-koe.md</code>, <code>hanzo/hanzo-engine.md</code>, <code>hanzo/hanzo-ml.md</code></p>
|
|
<h2>Overview</h2>
|
|
<p>Mugen is a <strong>PyTorch framework for deep learning research on audio generation</strong>. It provides training and inference code for multiple state-of-the-art generative audio models: text-to-music (MusicGen), text-to-sound (AudioGen), neural audio codecs (EnCodec), multi-band diffusion decoding, non-autoregressive generation (MAGNeT), audio watermarking (AudioSeal), and joint conditioning (JASCO).</p>
|
|
<p>The core architecture is a <strong>transformer language model</strong> operating over quantized audio tokens from EnCodec, with text conditioning via T5 or CLAP embeddings. Model scales range from ~300M to ~3.3B parameters.</p>
|
|
<h3>Models Included</h3>
|
|
<p>| Model | Task | Description | |-------|------|-------------| | <strong>MusicGen</strong> | Text-to-music | Controllable music generation with melody conditioning | | <strong>AudioGen</strong> | Text-to-sound | General audio/sound effect generation | | <strong>EnCodec</strong> | Audio codec | High-fidelity neural audio tokenizer | | <strong>Multi-Band Diffusion</strong> | Decoder | Diffusion-based EnCodec decoder for improved quality | | <strong>MAGNeT</strong> | Text-to-music/sound | Non-autoregressive masked generation | | <strong>AudioSeal</strong> | Watermarking | Imperceptible audio watermarking | | <strong>MusicGen Style</strong> | Style-to-music | Text + style conditioning | | <strong>JASCO</strong> | Multi-conditioned | Chords, melodies, drums + text conditioning |</p>
|
|
<h2>When to use</h2>
|
|
<ul><li>Text-conditioned music or sound effect generation</li><li>Training custom audio generation models on proprietary data</li><li>Neural audio compression/tokenization (EnCodec)</li><li>Audio watermarking for generated content</li><li>Research into transformer-based audio generative models</li></ul>
|
|
<h2>Hard requirements</h2>
|
|
<ol><li><strong>Python 3.9+</strong> with PyTorch 2.1</li><li><strong>GPU recommended</strong> for training and fast inference</li><li><strong>ffmpeg</strong> installed (system or conda)</li><li><strong>xformers < 0.0.23</strong> for memory-efficient attention</li></ol>
|
|
<h2>Quick reference</h2>
|
|
<p>| Item | Value | |------|-------| | Repo | <code>github.com/hanzoai/mugen</code> | | Branch | <code>main</code> | | Language | Python | | Package | <code>audiocraft</code> v1.4.0a2 | | Install | <code>pip install -e .</code> | | Train | Hydra-based: <code>dora run</code> | | Test | <code>make tests</code> | | Lint | <code>make linter</code> | | License | MIT (code), CC-BY-NC 4.0 (weights) |</p>
|
|
<h2>Architecture</h2>
|
|
<h3>Transformer Language Model</h3>
|
|
<p>The core generative model is an autoregressive transformer operating on EnCodec audio tokens:</p>
|
|
<pre><code>Text Prompt: "epic orchestral music with drums"
|
|
|
|
|
v
|
|
┌────────────────────────────────┐
|
|
│ Conditioning │
|
|
│ T5 / CLAP text embeddings │
|
|
│ + optional: chroma, chords, │
|
|
│ drums, melody, style │
|
|
│ ConditionFuser (cross-attn │
|
|
│ or prepend or input_interp) │
|
|
└──────────┬─────────────────────┘
|
|
|
|
|
v
|
|
┌────────────────────────────────┐
|
|
│ Streaming Transformer LM │
|
|
│ Codebook pattern: parallel │
|
|
│ n_q codebook streams (8) │
|
|
│ card: 1024 (codebook size) │
|
|
│ │
|
|
│ Configurable scale: │
|
|
│ small: dim=512, 8 layers │
|
|
│ base: dim=1024, 24 layers │
|
|
│ medium: dim=1536, 32 layers │
|
|
│ large: dim=2048, 48 layers │
|
|
│ │
|
|
│ Positional: sin/rope/sin_rope │
|
|
│ Attention: causal, streaming │
|
|
│ Optional: xformers flash attn │
|
|
│ CFG: classifier-free guidance │
|
|
└──────────┬─────────────────────┘
|
|
|
|
|
v
|
|
┌────────────────────────────────┐
|
|
│ EnCodec Decoder │
|
|
│ (or Multi-Band Diffusion) │
|
|
│ Audio tokens -> waveform │
|
|
│ 16kHz (sound) / 32kHz (music) │
|
|
└────────────────────────────────┘</code></pre>
|
|
<h3>Model Scale Configurations</h3>
|
|
<p>| Scale | dim | Heads | Layers | ~Params | |-------|-----|-------|--------|---------| | small | 512 | 8 | 8 | ~300M | | base | 1024 | 16 | 24 | ~1.5B | | medium | 1536 | 24 | 32 | ~2.2B | | large | 2048 | 32 | 48 | ~3.3B |</p>
|
|
<h3>EnCodec (Neural Audio Codec)</h3>
|
|
<ul><li>SEANet encoder/decoder architecture</li><li>Residual Vector Quantization (RVQ) with configurable codebooks (n_q=8 default)</li><li>1024 codes per codebook</li><li>Supports 16kHz and 32kHz sample rates</li><li>Streaming capable for real-time applications</li></ul>
|
|
<h2>One-file quickstart</h2>
|
|
<h3>Music Generation</h3>
|
|
<pre><code class="lang-python">import torchaudio
|
|
from audiocraft.models import MusicGen
|
|
|
|
model = MusicGen.get_pretrained("facebook/musicgen-melody")
|
|
model.set_generation_params(duration=8)
|
|
|
|
# Text-conditioned
|
|
wav = model.generate(["epic cinematic orchestral soundtrack"])
|
|
|
|
# Melody-conditioned
|
|
melody, sr = torchaudio.load("melody.wav")
|
|
wav = model.generate_with_chroma(
|
|
["epic cinematic version"],
|
|
melody[None].expand(1, -1, -1),
|
|
sr,
|
|
)
|
|
|
|
# Save output
|
|
torchaudio.save("output.wav", wav[0].cpu(), model.sample_rate)</code></pre>
|
|
<h3>Sound Effect Generation</h3>
|
|
<pre><code class="lang-python">from audiocraft.models import AudioGen
|
|
|
|
model = AudioGen.get_pretrained("facebook/audiogen-medium")
|
|
model.set_generation_params(duration=5)
|
|
|
|
wav = model.generate(["sirens and a humming engine approach and pass"])</code></pre>
|
|
<h3>Audio Compression</h3>
|
|
<pre><code class="lang-python">from audiocraft.models import EncodecModel
|
|
|
|
model = EncodecModel.encodec_model_24khz()
|
|
model.set_target_bandwidth(6.0)
|
|
|
|
wav = torch.randn(1, 1, 24000) # 1 second at 24kHz
|
|
encoded = model.encode(wav)
|
|
decoded = model.decode(encoded)</code></pre>
|
|
<h2>Training</h2>
|
|
<p>Training uses Facebook's Dora experiment manager with Hydra configs:</p>
|
|
<pre><code class="lang-bash"># Install with training deps
|
|
pip install -e '.[dev]'
|
|
|
|
# Run training (example: MusicGen base at 32kHz)
|
|
dora run solver=musicgen/musicgen_base_32khz
|
|
|
|
# Custom training config
|
|
dora run solver=musicgen/musicgen_base_32khz \
|
|
dataset.batch_size=8 \
|
|
optim.epochs=100 \
|
|
transformer_lm.dim=1024 \
|
|
transformer_lm.num_layers=24</code></pre>
|
|
<h3>Hydra Config Structure</h3>
|
|
<pre><code>config/
|
|
├── augmentations/default.yaml
|
|
├── conditioner/
|
|
│ ├── text2music.yaml # T5 text conditioning
|
|
│ ├── text2sound.yaml # Text for sound generation
|
|
│ ├── chroma2music.yaml # Chromagram conditioning
|
|
│ ├── chords2music.yaml # Chord conditioning
|
|
│ ├── drums2music.yaml # Drum track conditioning
|
|
│ ├── style2music.yaml # Style embedding conditioning
|
|
│ └── jasco_chords_drums.yaml
|
|
├── dset/audio/ # Dataset configs
|
|
├── model/
|
|
│ ├── encodec/ # Codec model configs
|
|
│ └── lm/
|
|
│ ├── default.yaml # Base LM config
|
|
│ └── model_scale/ # small/base/medium/large
|
|
└── config.yaml # Root config</code></pre>
|
|
<h2>Dependencies</h2>
|
|
<pre><code>torch==2.1.0
|
|
torchaudio>=2.0.0,<2.1.2
|
|
torchvision==0.16.0
|
|
av==11.0.0
|
|
einops
|
|
flashy>=0.0.1
|
|
hydra-core>=1.1
|
|
xformers<0.0.23
|
|
transformers>=4.31.0
|
|
demucs
|
|
librosa
|
|
soundfile
|
|
gradio
|
|
encodec
|
|
torchdiffeq</code></pre>
|
|
<h2>Project Structure</h2>
|
|
<pre><code>mugen/
|
|
├── audiocraft/
|
|
│ ├── __init__.py # v1.4.0a2
|
|
│ ├── models/
|
|
│ │ ├── musicgen.py # MusicGen model
|
|
│ │ ├── audiogen.py # AudioGen model
|
|
│ │ ├── encodec.py # EnCodec codec
|
|
│ │ ├── multibanddiffusion.py # Multi-band diffusion decoder
|
|
│ │ ├── magnet.py # MAGNeT model
|
|
│ │ ├── jasco.py # JASCO multi-conditioned
|
|
│ │ ├── watermark.py # AudioSeal watermarking
|
|
│ │ ├── lm.py # Core transformer LM
|
|
│ │ ├── lm_magnet.py # MAGNeT LM variant
|
|
│ │ ├── flow_matching.py # Flow matching model
|
|
│ │ ├── builders.py # Model factory
|
|
│ │ └── loaders.py # Checkpoint loading
|
|
│ ├── modules/
|
|
│ │ ├── transformer.py # StreamingTransformer
|
|
│ │ ├── conditioners.py # Text/audio/chroma conditioners
|
|
│ │ ├── codebooks_patterns.py # Parallel/delay codebook patterns
|
|
│ │ ├── seanet.py # SEANet encoder/decoder
|
|
│ │ ├── conv.py # Causal/streaming convolutions
|
|
│ │ ├── rope.py # Rotary positional embeddings
|
|
│ │ └── streaming.py # Streaming inference support
|
|
│ ├── solvers/
|
|
│ │ ├── musicgen.py # MusicGen training solver
|
|
│ │ ├── audiogen.py # AudioGen training solver
|
|
│ │ ├── compression.py # EnCodec training solver
|
|
│ │ ├── diffusion.py # Diffusion training solver
|
|
│ │ ├── magnet.py # MAGNeT training solver
|
|
│ │ ├── jasco.py # JASCO training solver
|
|
│ │ └── watermark.py # Watermark training solver
|
|
│ ├── data/ # Dataset loading and processing
|
|
│ ├── losses/ # Training losses (balancer, STFT, loudness)
|
|
│ ├── metrics/ # FAD, KLD, CLAP, PESQ, ViSQOL
|
|
│ ├── adversarial/ # GAN discriminators (MPD, MSD, MSSTFTD)
|
|
│ ├── optim/ # Optimizers, schedulers, EMA, FSDP
|
|
│ ├── quantization/ # RVQ implementation
|
|
│ ├── grids/ # Dora experiment grids
|
|
│ ├── utils/ # Utilities, caching, checkpoints
|
|
│ └── train.py # Training entry point
|
|
├── config/ # Hydra configs
|
|
├── assets/ # Example audio files
|
|
├── setup.py
|
|
├── Makefile
|
|
└── requirements.txt</code></pre>
|
|
<h2>Related Skills</h2>
|
|
<ul><li><code>hanzo/hanzo-koe.md</code> - Text-to-dialogue model (speech-specific)</li><li><code>hanzo/hanzo-engine.md</code> - Model serving infrastructure</li><li><code>hanzo/hanzo-ml.md</code> - Rust ML framework</li><li><code>hanzo/hanzo-candle.md</code> - Candle audio model support (Whisper, EnCodec)</li></ul>
|
|
<hr>
|
|
<p><strong>Last Updated</strong>: 2026-03-13 <strong>Category</strong>: Hanzo Ecosystem <strong>Related</strong>: audio, music-generation, sound-effects, codec, tts, watermarking <strong>Prerequisites</strong>: Python, PyTorch, audio processing, Hydra config</p>
|
|
<footer>
|
|
<div class="fmap">
|
|
<div><b>Build</b>
|
|
<a href="https://hanzo.app">hanzo.app</a> app builder
|
|
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
|
|
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
|
|
<div><b>Run</b>
|
|
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
|
|
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
|
|
<div><b>Account</b>
|
|
<a href="https://hanzo.id">hanzo.id</a> sign in
|
|
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
|
|
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
|
|
<div><b>Company</b>
|
|
<a href="https://hanzo.ai">hanzo.ai</a> canonical
|
|
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
|
|
</div>
|
|
<div class="fend"><a href="/hanzo-mugen.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
|
|
</footer>
|
|
</div></body></html> |