Audiocraft 音频生成

用于音频生成的 PyTorch 库，包括文本到音乐（MusicGen）和文本到声音（AudioGen）。当您需要从文本描述生成音乐、创建音效或执行旋律条件音乐生成时使用。

技能元数据


来源	捆绑（默认安装）
路径	`skills/mlops/models/audiocraft`
版本	`1.0.0`
作者	Orchestra Research
许可证	MIT
依赖项	`audiocraft`, `torch>=2.0.0`, `transformers>=4.30.0`
标签	`Multimodal`, `Audio Generation`, `Text-to-Music`, `Text-to-Audio`, `MusicGen`

参考：完整 SKILL.md

信息

以下是 Hermes 在触发此技能时加载的完整技能定义。这是技能激活时代理看到的指令。

AudioCraft：音频生成

使用 MusicGen、AudioGen 和 EnCodec 通过 Meta 的 AudioCraft 进行文本到音乐和文本到音频生成的综合指南。

何时使用 AudioCraft

在以下情况使用 AudioCraft：

需要从文本描述生成音乐
创建音效和环境音频
构建音乐生成应用程序
需要旋律条件音乐生成
想要立体声音频输出
需要具有风格迁移的可控音乐生成

主要功能：

MusicGen：具有旋律条件的文本到音乐生成
AudioGen：文本到音效生成
EnCodec：高保真神经音频编解码器
多种模型尺寸：从小型（300M）到大型（3.3B）
立体声支持：全立体声音频生成
风格条件：MusicGen-Style 用于基于参考的生成

改用替代方案：

Stable Audio：用于更长的商业音乐生成
Bark：用于带有音乐/音效的文本到语音
Riffusion：用于基于频谱图的音乐生成
OpenAI Jukebox：用于带有歌词的原始音频生成

快速开始

安装

# From PyPI
pip install audiocraft

# From GitHub (latest)
pip install git+https://github.com/facebookresearch/audiocraft.git

# Or use HuggingFace Transformers
pip install transformers torch torchaudio

基本文本到音乐（AudioCraft）

import torchaudio
from audiocraft.models import MusicGen

# Load model
model = MusicGen.get_pretrained('facebook/musicgen-small')

# Set generation parameters
model.set_generation_params(
    duration=8,  # seconds
    top_k=250,
    temperature=1.0
)

# Generate from text
descriptions = ["happy upbeat electronic dance music with synths"]
wav = model.generate(descriptions)

# Save audio
torchaudio.save("output.wav", wav[0].cpu(), sample_rate=32000)

使用 HuggingFace Transformers

from transformers import AutoProcessor, MusicgenForConditionalGeneration
import scipy

# Load model and processor
processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
model.to("cuda")

# Generate music
inputs = processor(
    text=["80s pop track with bassy drums and synth"],
    padding=True,
    return_tensors="pt"
).to("cuda")

audio_values = model.generate(
    **inputs,
    do_sample=True,
    guidance_scale=3,
    max_new_tokens=256
)

# Save
sampling_rate = model.config.audio_encoder.sampling_rate
scipy.io.wavfile.write("output.wav", rate=sampling_rate, data=audio_values[0, 0].cpu().numpy())

使用 AudioGen 进行文本到声音生成

from audiocraft.models import AudioGen

# Load AudioGen
model = AudioGen.get_pretrained('facebook/audiogen-medium')

model.set_generation_params(duration=5)

# Generate sound effects
descriptions = ["dog barking in a park with birds chirping"]
wav = model.generate(descriptions)

torchaudio.save("sound.wav", wav[0].cpu(), sample_rate=16000)

核心概念

架构概述

AudioCraft Architecture:
┌──────────────────────────────────────────────────────────────┐
│                    Text Encoder (T5)                          │
│                         │                                     │
│                    Text Embeddings                            │
└────────────────────────┬─────────────────────────────────────┘
                         │
┌────────────────────────▼─────────────────────────────────────┐
│              Transformer Decoder (LM)                         │
│     Auto-regressively generates audio tokens                  │
│     Using efficient token interleaving patterns               │
└────────────────────────┬─────────────────────────────────────┘
                         │
┌────────────────────────▼─────────────────────────────────────┐
│                EnCodec Audio Decoder                          │
│        Converts tokens back to audio waveform                 │
└──────────────────────────────────────────────────────────────┘

模型变体

模型	尺寸	描述	用例
`musicgen-small`	300M	文本到音乐	快速生成
`musicgen-medium`	1.5B	文本到音乐	平衡型
`musicgen-large`	3.3B	文本到音乐	最佳质量
`musicgen-melody`	1.5B	文本 + 旋律	旋律条件
`musicgen-melody-large`	3.3B	文本 + 旋律	最佳旋律
`musicgen-stereo-*`	可变	立体声输出	立体声生成
`musicgen-style`	1.5B	风格迁移	基于参考
`audiogen-medium`	1.5B	文本到声音	音效

生成参数

参数	默认值	描述
`duration`	8.0	长度（秒）（1-120）
`top_k`	250	Top-k 采样
`top_p`	0.0	核采样（0 = 禁用）
`temperature`	1.0	采样温度
`cfg_coef`	3.0	无分类器引导

MusicGen 用法

文本到音乐生成

from audiocraft.models import MusicGen
import torchaudio

model = MusicGen.get_pretrained('facebook/musicgen-medium')

# Configure generation
model.set_generation_params(
    duration=30,          # Up to 30 seconds
    top_k=250,            # Sampling diversity
    top_p=0.0,            # 0 = use top_k only
    temperature=1.0,      # Creativity (higher = more varied)
    cfg_coef=3.0          # Text adherence (higher = stricter)
)

# Generate multiple samples
descriptions = [
    "epic orchestral soundtrack with strings and brass",
    "chill lo-fi hip hop beat with jazzy piano",
    "energetic rock song with electric guitar"
]

# Generate (returns [batch, channels, samples])
wav = model.generate(descriptions)

# Save each
for i, audio in enumerate(wav):
    torchaudio.save(f"music_{i}.wav", audio.cpu(), sample_rate=32000)

旋律条件生成

from audiocraft.models import MusicGen
import torchaudio

# Load melody model
model = MusicGen.get_pretrained('facebook/musicgen-melody')
model.set_generation_params(duration=30)

# Load melody audio
melody, sr = torchaudio.load("melody.wav")

# Generate with melody conditioning
descriptions = ["acoustic guitar folk song"]
wav = model.generate_with_chroma(descriptions, melody, sr)

torchaudio.save("melody_conditioned.wav", wav[0].cpu(), sample_rate=32000)

立体声生成

from audiocraft.models import MusicGen

# Load stereo model
model = MusicGen.get_pretrained('facebook/musicgen-stereo-medium')
model.set_generation_params(duration=15)

descriptions = ["ambient electronic music with wide stereo panning"]
wav = model.generate(descriptions)

# wav shape: [batch, 2, samples] for stereo
print(f"Stereo shape: {wav.shape}")  # [1, 2, 480000]
torchaudio.save("stereo.wav", wav[0].cpu(), sample_rate=32000)

音频续写

from transformers import AutoProcessor, MusicgenForConditionalGeneration

processor = AutoProcessor.from_pretrained("facebook/musicgen-medium")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-medium")

# Load audio to continue
import torchaudio
audio, sr = torchaudio.load("intro.wav")

# Process with text and audio
inputs = processor(
    audio=audio.squeeze().numpy(),
    sampling_rate=sr,
    text=["continue with a epic chorus"],
    padding=True,
    return_tensors="pt"
)

# Generate continuation
audio_values = model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=512)

MusicGen-Style 用法

风格条件生成

from audiocraft.models import MusicGen

# Load style model
model = MusicGen.get_pretrained('facebook/musicgen-style')

# Configure generation with style
model.set_generation_params(
    duration=30,
    cfg_coef=3.0,
    cfg_coef_beta=5.0  # Style influence
)

# Configure style conditioner
model.set_style_conditioner_params(
    eval_q=3,          # RVQ quantizers (1-6)
    excerpt_length=3.0  # Style excerpt length
)

# Load style reference
style_audio, sr = torchaudio.load("reference_style.wav")

# Generate with text + style
descriptions = ["upbeat dance track"]
wav = model.generate_with_style(descriptions, style_audio, sr)

纯风格生成（无文本）

# Generate matching style without text prompt
model.set_generation_params(
    duration=30,
    cfg_coef=3.0,
    cfg_coef_beta=None  # Disable double CFG for style-only
)

wav = model.generate_with_style([None], style_audio, sr)

AudioGen 用法

音效生成

from audiocraft.models import AudioGen
import torchaudio

model = AudioGen.get_pretrained('facebook/audiogen-medium')
model.set_generation_params(duration=10)

# Generate various sounds
descriptions = [
    "thunderstorm with heavy rain and lightning",
    "busy city traffic with car horns",
    "ocean waves crashing on rocks",
    "crackling campfire in forest"
]

wav = model.generate(descriptions)

for i, audio in enumerate(wav):
    torchaudio.save(f"sound_{i}.wav", audio.cpu(), sample_rate=16000)

EnCodec 用法

音频压缩

from audiocraft.models import CompressionModel
import torch
import torchaudio

# Load EnCodec
model = CompressionModel.get_pretrained('facebook/encodec_32khz')

# Load audio
wav, sr = torchaudio.load("audio.wav")

# Ensure correct sample rate
if sr != 32000:
    resampler = torchaudio.transforms.Resample(sr, 32000)
    wav = resampler(wav)

# Encode to tokens
with torch.no_grad():
    encoded = model.encode(wav.unsqueeze(0))
    codes = encoded[0]  # Audio codes

# Decode back to audio
with torch.no_grad():
    decoded = model.decode(codes)

torchaudio.save("reconstructed.wav", decoded[0].cpu(), sample_rate=32000)

常见工作流

工作流 1：音乐生成流水线

import torch
import torchaudio
from audiocraft.models import MusicGen

class MusicGenerator:
    def __init__(self, model_name="facebook/musicgen-medium"):
        self.model = MusicGen.get_pretrained(model_name)
        self.sample_rate = 32000

    def generate(self, prompt, duration=30, temperature=1.0, cfg=3.0):
        self.model.set_generation_params(
            duration=duration,
            top_k=250,
            temperature=temperature,
            cfg_coef=cfg
        )

        with torch.no_grad():
            wav = self.model.generate([prompt])

        return wav[0].cpu()

    def generate_batch(self, prompts, duration=30):
        self.model.set_generation_params(duration=duration)

        with torch.no_grad():
            wav = self.model.generate(prompts)

        return wav.cpu()

    def save(self, audio, path):
        torchaudio.save(path, audio, sample_rate=self.sample_rate)

# Usage
generator = MusicGenerator()
audio = generator.generate(
    "epic cinematic orchestral music",
    duration=30,
    temperature=1.0
)
generator.save(audio, "epic_music.wav")

工作流 2：声音设计批处理

import json
from pathlib import Path
from audiocraft.models import AudioGen
import torchaudio

def batch_generate_sounds(sound_specs, output_dir):
    """
    Generate multiple sounds from specifications.

    Args:
        sound_specs: list of {"name": str, "description": str, "duration": float}
        output_dir: output directory path
    """
    model = AudioGen.get_pretrained('facebook/audiogen-medium')
    output_dir = Path(output_dir)
    output_dir.mkdir(exist_ok=True)

    results = []

    for spec in sound_specs:
        model.set_generation_params(duration=spec.get("duration", 5))

        wav = model.generate([spec["description"]])

        output_path = output_dir / f"{spec['name']}.wav"
        torchaudio.save(str(output_path), wav[0].cpu(), sample_rate=16000)

        results.append({
            "name": spec["name"],
            "path": str(output_path),
            "description": spec["description"]
        })

    return results

# Usage
sounds = [
    {"name": "explosion", "description": "massive explosion with debris", "duration": 3},
    {"name": "footsteps", "description": "footsteps on wooden floor", "duration": 5},
    {"name": "door", "description": "wooden door creaking and closing", "duration": 2}
]

results = batch_generate_sounds(sounds, "sound_effects/")

工作流 3：Gradio 演示

import gradio as gr
import torch
import torchaudio
from audiocraft.models import MusicGen

model = MusicGen.get_pretrained('facebook/musicgen-small')

def generate_music(prompt, duration, temperature, cfg_coef):
    model.set_generation_params(
        duration=duration,
        temperature=temperature,
        cfg_coef=cfg_coef
    )

    with torch.no_grad():
        wav = model.generate([prompt])

    # Save to temp file
    path = "temp_output.wav"
    torchaudio.save(path, wav[0].cpu(), sample_rate=32000)
    return path

demo = gr.Interface(
    fn=generate_music,
    inputs=[
        gr.Textbox(label="Music Description", placeholder="upbeat electronic dance music"),
        gr.Slider(1, 30, value=8, label="Duration (seconds)"),
        gr.Slider(0.5, 2.0, value=1.0, label="Temperature"),
        gr.Slider(1.0, 10.0, value=3.0, label="CFG Coefficient")
    ],
    outputs=gr.Audio(label="Generated Music"),
    title="MusicGen Demo"
)

demo.launch()

性能优化

内存优化

# Use smaller model
model = MusicGen.get_pretrained('facebook/musicgen-small')

# Clear cache between generations
torch.cuda.empty_cache()

# Generate shorter durations
model.set_generation_params(duration=10)  # Instead of 30

# Use half precision
model = model.half()

批处理效率

# Process multiple prompts at once (more efficient)
descriptions = ["prompt1", "prompt2", "prompt3", "prompt4"]
wav = model.generate(descriptions)  # Single batch

# Instead of
for desc in descriptions:
    wav = model.generate([desc])  # Multiple batches (slower)

GPU 内存要求

模型	FP32 显存	FP16 显存
musicgen-small	~4GB	~2GB
musicgen-medium	~8GB	~4GB
musicgen-large	~16GB	~8GB

常见问题

问题	解决方案
CUDA OOM	使用较小的模型，减少持续时间
质量差	增加 cfg_coef，使用更好的提示词
生成时间太短	检查最大持续时间设置
音频伪影	尝试不同的温度
立体声不起作用	使用立体声模型变体

参考资料

高级用法 - 训练、微调、部署
故障排除 - 常见问题及解决方案

资源

GitHub: https://github.com/facebookresearch/audiocraft
论文 (MusicGen): https://arxiv.org/abs/2306.05284
论文 (AudioGen): https://arxiv.org/abs/2209.15352
HuggingFace: https://huggingface.co/facebook/musicgen-small
演示: https://huggingface.co/spaces/facebook/MusicGen

技能元数据​

参考：完整 SKILL.md​

AudioCraft：音频生成

何时使用 AudioCraft​

快速开始​

安装​

基本文本到音乐（AudioCraft）​

使用 HuggingFace Transformers​

使用 AudioGen 进行文本到声音生成​

核心概念​

架构概述​

模型变体​

生成参数​

MusicGen 用法​

文本到音乐生成​

旋律条件生成​

立体声生成​

音频续写​

MusicGen-Style 用法​

风格条件生成​

纯风格生成（无文本）​

AudioGen 用法​

音效生成​

EnCodec 用法​

音频压缩​

常见工作流​

工作流 1：音乐生成流水线​

工作流 2：声音设计批处理​

工作流 3：Gradio 演示​

性能优化​

内存优化​

批处理效率​

GPU 内存要求​

常见问题​

参考资料​

资源​