Wiki-Quellcode von Audiocraft Plus Soundeffects

Zuletzt geändert von René Schmidt am 2025/04/03 00:21
Verstecke letzte Bearbeiter
René Schmidt 1.1 1 = AudioCraft Plus =
2
3
4 [[~[~[image:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_docs/badge.svg~|~|alt="docs badge"~]~]>>url:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_docs/badge.svg]] [[~[~[image:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_linter/badge.svg~|~|alt="linter badge"~]~]>>url:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_linter/badge.svg]] [[~[~[image:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_tests/badge.svg~|~|alt="tests badge"~]~]>>url:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_tests/badge.svg]]
5
6 AudioCraft is a PyTorch library for deep learning research on audio generation. AudioCraft contains inference and training code for two state-of-the-art AI generative models producing high-quality audio: AudioGen and MusicGen.
7
8 [[~[~[image:https://camo.githubusercontent.com/96889048f8a9014fdeba2a891f97150c6aac6e723f5190236b10215a97ed41f3/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667~|~|alt="Open In Colab"~]~] >>url:https://colab.research.google.com/github/camenduru/MusicGen-colab/blob/main/MusicGen_ClownOfMadness_plus_colab.ipynb]][[~[~[image:https://camo.githubusercontent.com/8436d0dbd9d29c58bfece9bf36e6cbdc6b38db1280c5007cad21f16debf04f39/68747470733a2f2f68756767696e67666163652e636f2f64617461736574732f68756767696e67666163652f6261646765732f7261772f6d61696e2f6f70656e2d696e2d68662d7370616365732d736d2e737667~|~|alt="Open in HugginFace"~]~] >>url:https://huggingface.co/spaces/facebook/MusicGen]]
9
10
11 [[~[~[image:https://private-user-images.githubusercontent.com/52707645/262005171-043fc037-54a9-48c4-bb5c-bf9b7440d146.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.B0CaQAdeqzKGnrTqpzlp-HynG8FCndhlBmUhoMJmdNk~|~|alt="image"~]~]>>url:https://private-user-images.githubusercontent.com/52707645/262005171-043fc037-54a9-48c4-bb5c-bf9b7440d146.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.B0CaQAdeqzKGnrTqpzlp-HynG8FCndhlBmUhoMJmdNk]]
12
13 == Features ==
14
15
16 AudioCraft Plus is an all-in-one WebUI for the original AudioCraft, adding many quality features on top.
17
18 * AudioGen Model
19 * Multiband Diffusion
20 * Custom Model Support
21 * Generation Metadata and Audio Info tab
22 * Mono to Stereo
23 * Multiprompt/Prompt Segmentation with Structure Prompts
24 * Video Output Customization
25 * Music Continuation
26
27 == Installation ==
28
29
30 If you are updating from the previous version of AudioCraft Plus, do the following steps in the AudioCraft Plus folder:
31
32 {{{git pull
33 pip install transformers --upgrade
34 pip install torchmetrics --upgrade}}}
35
36 ==== Otherwise: Clean Installation ====
37
38
39 AudioCraft requires Python 3.9, PyTorch 2.0.0. To install AudioCraft, you can run the following:
40
41 {{{# Best to make sure you have torch installed first, in particular before installing xformers.
42 # Don't run this if you already have PyTorch installed.
43 pip install 'torch>=2.0'
44 # Then proceed to one of the following
45 pip install -U audiocraft # stable release
46 pip install -U git+https://git@github.com/GrandaddyShmax/audiocraft_plus#egg=audiocraft # bleeding edge
47 pip install -e . # or if you cloned the repo locally (mandatory if you want to train).}}}
48
49 We also recommend having ffmpeg installed, either through your system or Anaconda:
50
51 {{{sudo apt-get install ffmpeg
52 # Or if you are using Anaconda or Miniconda
53 conda install 'ffmpeg<5' -c conda-forge}}}
54
55 Installation video thanks to Pogs Cafe:
56 [[~[~[image:https://camo.githubusercontent.com/c5016f10ef6646ee645337023b4e04376adccd63f10e9a9a580ca1a0c2f1ac6e/687474703a2f2f696d672e796f75747562652e636f6d2f76692f576a476b34626362554f492f302e6a7067~|~|alt="Untitled"~]~]>>url:http://www.youtube.com/watch?v=WjGk4bcbUOI]]
57
58 Additional installation guide by [[radaevm>>url:https://github.com/radaevm]] can be found [[HERE>>url:https://github.com/GrandaddyShmax/audiocraft_plus/discussions/31]]
59
60 == Models ==
61
62
63 At the moment, AudioCraft contains the training code and inference code for:
64
65 * [[MusicGen>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/MUSICGEN.md]]: A state-of-the-art controllable text-to-music model.
66 * [[AudioGen>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/AUDIOGEN.md]]: A state-of-the-art text-to-sound model.
67 * [[EnCodec>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/ENCODEC.md]]: A state-of-the-art high fidelity neural audio codec.
68 * [[Multi Band Diffusion>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/MBD.md]]: An EnCodec compatible decoder using diffusion.
69
70 == Training code ==
71
72
73 AudioCraft contains PyTorch components for deep learning research in audio and training pipelines for the developed models. For a general introduction of AudioCraft design principles and instructions to develop your own training pipeline, refer to the [[AudioCraft training documentation>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/TRAINING.md]].
74
75 For reproducing existing work and using the developed training pipelines, refer to the instructions for each specific model that provides pointers to configuration, example grids and model/task-specific information and FAQ.
76
77 == API documentation ==
78
79
80 We provide some [[API documentation>>url:https://facebookresearch.github.io/audiocraft/api_docs/audiocraft/index.html]] for AudioCraft.
81
82 == FAQ ==
83
84
85 ==== Is the training code available? ====
86
87
88 Yes! We provide the training code for [[EnCodec>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/ENCODEC.md]], [[MusicGen>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/MUSICGEN.md]] and [[Multi Band Diffusion>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/docs/MBD.md]].
89
90 ==== Where are the models stored? ====
91
92
93 Hugging Face stored the model in a specific location, which can be overriden by setting the AUDIOCRAFT_CACHE_DIR environment variable.
94
95 == License ==
96
97
98 * The code in this repository is released under the MIT license as found in the [[LICENSE file>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/LICENSE]].
99 * The models weights in this repository are released under the CC-BY-NC 4.0 license as found in the [[LICENSE_weights file>>url:https://github.com/GrandaddyShmax/audiocraft_plus/blob/main/LICENSE_weights]].

Anwendungen

Navigation

Benötigen Sie Hilfe?

Wenn Sie Hilfe mit XWiki benötigen, wenden Sie sich an: