Skip to content

Add Freesound-trained models #64

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
palonso merged 1 commit into from
Apr 7, 2026
Merged

Add Freesound-trained models #64

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,13 +133,16 @@ Output:
| **multifeature** | audio | 18.75 | 24000 | .467 | 1.76 | .938 | .734 | .833 | .623 |
| **multifeature-25hz** | audio | 25 | 24000 | .463 | 1.79 | .932 | .728 | .848 | .628 |
| **multifeature-25hz-fsq** | audio | 25 | 24000 | .463 | 1.71 | **.940**| **.749**| **.855**| .628 |
| **base-freesound-small** | mel | 15.63 | 16000 | - | - | - | - | - | - |
| **base-freesound-large** | mel | 15.63 | 16000 | - | - | - | - | - | - |

> **Note:** Different models were trained with different sample rates.
> It is responsibility of the user to ensure that the input audio is sampled at the correct rate.

OMAR-RQ models are offered in different configurations, each with its own strengths and weaknesses.
Models based on mel spectrogram (**base** and **multicodebook**) tend to perform better on semantic tasks such as auto-tagging, structure recognition, and difficulty estimation.
On the other hand, **multifeature-24hz-fsq** offers the best performance in tonal and temporal tasks such as pitch and chord estimation, and beat tracking.
The **base-freesound-small** and **base-freesound-large** models were trained with [Freesound](https://freesound.org/) data.

### Hugging Face Model IDs

Expand All @@ -148,6 +151,8 @@ On the other hand, **multifeature-24hz-fsq** offers the best performance in tona
- [mtg-upf/omar-rq-multifeature](https://huggingface.co/mtg-upf/omar-rq-multifeature)
- [mtg-upf/omar-rq-multifeature-25hz](https://huggingface.co/mtg-upf/omar-rq-multifeature-25hz)
- [mtg-upf/omar-rq-multifeature-25hz-fsq](https://huggingface.co/mtg-upf/omar-rq-multifeature-25hz-fsq)
- [mtg-upf/omar-rq-base-freesound-small](https://huggingface.co/mtg-upf/omar-rq-base-freesound-small)
- [mtg-upf/omar-rq-base-freesound-large](https://huggingface.co/mtg-upf/omar-rq-base-freesound-large)

## Pre-training OMAR-RQ models

Expand Down
1 change: 1 addition & 0 deletions tests/test_omar_rq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
"mtg-upf/omar-rq-multifeature-25hz",
"mtg-upf/omar-rq-multifeature-25hz-fsq",
"mtg-upf/omar-rq-base-freesound-small",
"mtg-upf/omar-rq-base-freesound-large",
]


Expand Down
Loading