musicaudiopretrain
commited on
Commit
β’
c40b01f
1
Parent(s):
07ee9c5
Update README.md
Browse files
README.md
CHANGED
@@ -10,6 +10,7 @@ pinned: false
|
|
10 |
We are a group of people working towards Music AGI (Artificial General Intelligence)~ We pre-train large music models (LMMs)~π₯
|
11 |
|
12 |
The development log of our Music Audio Pre-training (m-a-p) model family:
|
|
|
13 |
- 17/03/2023: we release two advanced music understanding models, [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) and [MERT-v1-330M](https://huggingface.co/m-a-p/MERT-v1-330M) , trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks.
|
14 |
- 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset [MERT-v0-public](https://huggingface.co/m-a-p/MERT-v0-public)
|
15 |
- 29/12/2022: a music understanding model [MERT-v0](https://huggingface.co/m-a-p/MERT-v0) trained with **MLM** paradigm, which performs better at downstream tasks.
|
|
|
10 |
We are a group of people working towards Music AGI (Artificial General Intelligence)~ We pre-train large music models (LMMs)~π₯
|
11 |
|
12 |
The development log of our Music Audio Pre-training (m-a-p) model family:
|
13 |
+
- 02/06/2023: officially release the [MERt pre-print paper](https://arxiv.org/abs/2306.00107) and training [codes](https://github.com/yizhilll/MERT).
|
14 |
- 17/03/2023: we release two advanced music understanding models, [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) and [MERT-v1-330M](https://huggingface.co/m-a-p/MERT-v1-330M) , trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks.
|
15 |
- 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset [MERT-v0-public](https://huggingface.co/m-a-p/MERT-v0-public)
|
16 |
- 29/12/2022: a music understanding model [MERT-v0](https://huggingface.co/m-a-p/MERT-v0) trained with **MLM** paradigm, which performs better at downstream tasks.
|