musicnn - GitLite

KO | EN

gitlite — search

#javascript #react #golang #machine-learning #deep-learning #linux #docker #macos #nodejs #java #windows #security #ios #openai

musicnn

(★ 719)

Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.

파일 탐색기

최종 버전 다운로드 (.zip)

- joram-moments_of_clarity-08-solipsism-59-88.mp3
- TRWJAZW128F42760DD_test.mp3
- musicnn-backend.png
- musicnn-frontend.png
- musicnn-midend.png
- musicnn.png
- musicnn_doc.png
- taggram.png
- vgg.png
- vgg_doc.png
- - .data-00000-of-00001
  - .index
  - .meta
  - checkpoint
  - config.json
  - experiment.result
  - train_log.tsv
- - .data-00000-of-00001
  - .index
  - .meta
  - checkpoint
  - config.json
  - experiment.result
  - train_log.tsv
- - .data-00000-of-00001
  - .index
  - .meta
  - checkpoint
  - config.json
  - experiment.result
  - train_log.tsv
- - .data-00000-of-00001
  - .index
  - .meta
  - checkpoint
  - config.json
  - experiment.result
  - train_log.tsv
- - .data-00000-of-00001
  - .index
  - .meta
  - checkpoint
  - config.json
  - experiment.result
  - train_log.tsv
- __init__.py
- configuration.py
- extractor.py
- models.py
- tagger.py
.gitignore
DOCUMENTATION.md
FAQs.md
LICENSE.md
MANIFEST.in
musicnn_example.ipynb
README.md
setup.py
tagging_example.ipynb
vgg_example.ipynb

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/jordipons/musicnn

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd musicnn

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

or, to get bigger models and all the documentation (including jupyter notebooks), install from source:

이 명령어를 터미널에 그대로 입력해 실행하세요.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# musicnn
Pronounced as "musician", `musicnn` is a set of pre-trained musically motivated convolutional neural networks for music audio tagging. This repository also includes some pre-trained [vgg-like](https://github.com/jordipons/musicnn/blob/master/vgg_example.ipynb) baselines.

Check the [documentation](https://github.com/jordipons/musicnn/blob/master/DOCUMENTATION.md) and our [basic](https://github.com/jordipons/musicnn/blob/master/tagging_example.ipynb) / [advanced](https://github.com/jordipons/musicnn/blob/master/musicnn_example.ipynb) examples to understand how to use `musicnn`.

Do you have questions? Check the [FAQs](https://github.com/jordipons/musicnn/blob/master/FAQs.md).

## Installation
```pip install musicnn```

or, to get bigger models and all the documentation (including jupyter notebooks), install from source:

``` git clone https://github.com/jordipons/musicnn.git```

``` python setup.py install```

## Predict tags

From within **python**, you can estimate the topN tags:
~~~~python
from musicnn.tagger import top_tags
top_tags('./audio/joram-moments_of_clarity-08-solipsism-59-88.mp3', model='MTT_musicnn', topN=10)
~~~~
>['techno', 'electronic', 'synth', 'fast', 'beat', 'drums', 'no vocals', 'no vocal', 'dance', 'ambient']

Let's try another song!

~~~~python
top_tags('./audio/TRWJAZW128F42760DD_test.mp3')
~~~~
>['guitar', 'piano', 'fast']

From the **command-line**, you can also print the topN tags on the screen:

~~~~
python -m musicnn.tagger file_name.ogg --print
python -m musicnn.tagger file_name.au --model 'MSD_musicnn' --topN 3 --length 3 --overlap 1.5 --print
~~~~~

or save to a file:

~~~~
python -m musicnn.tagger file_name.wav --save out.tags
python -m musicnn.tagger file_name.mp3 --model 'MTT_musicnn' --topN 10 --length 3 --overlap 1 --print --save out.tags
~~~~

## Extract the Taggram

You can also compute the taggram using **python** (see our [basic](https://github.com/jordipons/musicnn/blob/master/tagging_example.ipynb) example for more details on how to depict it):

~~~~python
from musicnn.extractor import extractor
taggram, tags = extractor('./audio/joram-moments_of_clarity-08-solipsism-59-88.mp3', model='MTT_musicnn')
~~~~
![Taggram](https://raw.githubusercontent.com/jordipons/musicnn/master/images/taggram.png "Taggram")

The above analyzed music clips are included in the `./audio/` folder of this repository.

You can listen to those and evaluate `musicnn` yourself!