|
1 | 1 | Interactive demos |
2 | 2 | ================= |
3 | 3 |
|
4 | | -Music audio descriptors in the browser |
5 | | --------------------------------------- |
| 4 | +Essentia.js browser demos — (real-time) analysis in the browser (tagging, genre, mood, key, BPM, onset detection, audio metering, chroma, pitch, mel-spectrogram) |
| 5 | +https://mtg.github.io/essentia.js/examples/#/demos/ |
6 | 6 |
|
7 | | -Examples of music audio analysis with Essentia algorithms using Essentia.js |
| 7 | +Replicate demos — cloud-hosted inference demos (tagging, genre, mood, arousal/valence, approachability, engagement, BPM) |
| 8 | +https://replicate.com/mtg/ |
8 | 9 |
|
9 | | -https://mtg.github.io/essentia.js/examples/ |
| 10 | +AcousticBrainz — large-scale music analysis database with descriptors for millions of tracks |
| 11 | +https://acousticbrainz.org |
10 | 12 |
|
11 | | - |
12 | | -Tempo estimation |
13 | | ----------------- |
14 | | - |
15 | | -Tempo BPM estimation with Essentia: https://replicate.com/mtg/essentia-bpm |
16 | | - |
17 | | - |
18 | | -Essentia TensorFlow models |
19 | | --------------------------- |
20 | | - |
21 | | -Examples of inference with the pre-trained TensorFlow models for music auto-tagging and classification tasks: |
22 | | - |
23 | | -- Music classification by genre, mood, danceability, instrumentation: https://replicate.com/mtg/music-classifiers |
24 | | -- Music style classification with the Discogs taxonomy (400 styles, MAEST model). Overall track-level predictions: https://replicate.com/mtg/maest |
25 | | -- Music style classification with the Discogs taxonomy (400 styles, Effnet-Discogs model). Overall track-level predictions: https://replicate.com/mtg/effnet-discogs |
26 | | -- Music style classification with the Discogs taxonomy (400 styles, Effnet-Discogs model). Segment-level real-time predictions with Essentia.js: https://essentia.upf.edu/essentiajs-discogs |
27 | | -- Real-time music autotagging (50 tags) in the browser with Essentia.js: https://mtg.github.io/essentia.js/examples/demos/autotagging-rt/ |
28 | | -- Mood classification in the browser with Essentia.js: https://mtg.github.io/essentia.js/examples/demos/mood-classifiers/ |
29 | | -- Music emotion arousal/valence regression: https://replicate.com/mtg/music-arousal-valence |
30 | | -- Music approachability and engagement: https://replicate.com/mtg/music-approachability-engagement |
31 | | -- Jupyter notebook for real-time music `auto-tagging <https://github.com/MTG/essentia/blob/master/src/examples/python/tutorial_tensorflow_real-time_auto-tagging.ipynb>`_ and `classification <https://github.com/MTG/essentia/blob/master/src/examples/python/tutorial_tensorflow_real-time_simultaneous_classifiers.ipynb>`_. |
32 | | - |
33 | | - .. raw:: html |
34 | | - |
35 | | - <iframe width="560" height="315" src="https://www.youtube.com/embed/xMUcY7_n4kQ" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> |
36 | | - |
37 | | - <iframe width="560" height="315" src="https://www.youtube.com/embed/yssBE6oafLs" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> |
38 | | - |
39 | | -Essentia SVM models |
40 | | -------------------- |
41 | | - |
42 | | -Examples of inference with older SVM models for music classification tasks: |
43 | | - |
44 | | -- `AcousticBrainz <https://acousticbrainz.org>`_ is using our pre-trained SVM classifiers for large-scale music analysis on millions of tracks. |
45 | | -- `AcousticBrainz Moods Playlist Generator <http://mtg.upf.edu/demos/acousticbrainz/moods>`_ is using SVM mood classifiers. |
| 13 | +Cosine.club — interactive music similarity exploration |
| 14 | +https://cosine.club/ |
0 commit comments