akanatas commited on
Commit
0655b33
verified
1 Parent(s): ed246f9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -26,8 +26,8 @@ library_name: transformers
26
  | [*Hindustani*](https://dunya.compmusic.upf.edu/hindustani/) | North Indian classical | 200h |
27
  | [*Carnatic*](https://dunya.compmusic.upf.edu/carnatic/) | South Indian classical | 200h |
28
 
29
- > 馃И The final model was merged using a scaling factor of **位 = 0.2**, which yielded the best overall performance across all task arithmetic variants evaluated.
30
 
 
31
 
32
 
33
  馃攢 This model serves as an alternative to [**CultureMERT-95M**](https://huggingface.co/ntua-slp/CultureMERT-95M). It merges culturally specialized models in weight space via task arithmetic to form a unified multi-cultural model. Each single-culture adapted model is obtained using the same two-stage continual pre-training strategy as CultureMERT-95M, applied separately to each musical tradition prior to merging.
 
26
  | [*Hindustani*](https://dunya.compmusic.upf.edu/hindustani/) | North Indian classical | 200h |
27
  | [*Carnatic*](https://dunya.compmusic.upf.edu/carnatic/) | South Indian classical | 200h |
28
 
 
29
 
30
+ > 馃И The final model was merged using a scaling factor of **位 = 0.2**, which yielded the best overall performance across all task arithmetic variants evaluated.
31
 
32
 
33
  馃攢 This model serves as an alternative to [**CultureMERT-95M**](https://huggingface.co/ntua-slp/CultureMERT-95M). It merges culturally specialized models in weight space via task arithmetic to form a unified multi-cultural model. Each single-culture adapted model is obtained using the same two-stage continual pre-training strategy as CultureMERT-95M, applied separately to each musical tradition prior to merging.