Update README.md

README.md

@@ -15,7 +15,8 @@ library_name: transformers
 # CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
 📑 [**Read the full paper (to be presented at ISMIR 2025)**](...TODO)
 
-**CultureMERT-TA-95M** is a multi-culturally adapted 95M-parameter music foundation model created by merging single-culture adaptations of [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) through **task arithmetic**. Instead of continual pre-training on a multi-cultural data mix, as done in [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M), we merge multiple single-culture adapted models, each continually pre-trained via our two-stage strategy on a distinct musical tradition:
+**CultureMERT-TA-95M** is a 95M-parameter music foundation model adapted to diverse musical cultures through **task arithmetic**. Instead of direct continual pre-training on a multi-cultural mixture, as in [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M), this model merges multiple **single-culture adapted** variants of [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M)—each continually pre-trained via our two-stage strategy on a distinct musical tradition:
+
 
 | Dataset         | Music Tradition             | Hours Used |
 |-----------------|-----------------------------|------------|
@@ -24,9 +25,10 @@ library_name: transformers
 | [*Hindustani*](https://dunya.compmusic.upf.edu/hindustani/) | North Indian classical      | 200h       |
 | [*Carnatic*](https://dunya.compmusic.upf.edu/carnatic/)     | South Indian classical      | 200h       |
 
-> 🧪 The final model was merged using a scaling factor of **λ = 0.2**, which yielded the best performance across all variants tested.
+> 🧪 The final model was merged using a scaling factor of **λ = 0.2**, which yielded the best overall performance across all task arithmetic variants evaluated.
+
 
-🔀 This is an alternative variant of [**CultureMERT-95M**](https://huggingface.co/ntua-slp/CultureMERT-95M), where culturally specialized models are merged in weight space via task arithmetic to form a unified multi-cultural model.
+🔀 This is an alternative variant of [**CultureMERT-95M**](https://huggingface.co/ntua-slp/CultureMERT-95M), where culturally specialized models are merged in weight space via task arithmetic to form a unified multi-cultural model. It builds directly on [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M), using the same two-stage continual pre-training strategy applied individually to each musical tradition before merging.
 
 ---
 
@@ -34,6 +36,7 @@ library_name: transformers
 
 We follow the exact same evaluation protocol as in [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M). Below are the evaluation results, along with comparisons to both [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M) and the original [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M):
 
+
 ## ROC-AUC / mAP
 
 | Model              | Turkish-makam | Hindustani | Carnatic | Lyra | FMA-medium | MTAT | **Avg.** |
@@ -52,7 +55,7 @@ We follow the exact same evaluation protocol as in [CultureMERT-95M](https://hug
 | **CultureMERT-TA-95M**  | 76.9% / 45.4% | 74.2% / 45.0% | 82.5% / 32.1% | 73.0% / **45.3%** | **59.1%** / **38.2%** | 35.7% / 21.5% | 52.4% |
 
 
-📈 **CultureMERT-TA-95M** performs comparably to [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M) on non-Western datasets and even surpasses it on *Lyra* and Western benchmarks. Notably, it also outperforms the [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) on Western tasks by a **+0.7%** average improvement.
+📈 **CultureMERT-TA-95M** performs comparably to [CultureMERT-95M](https://huggingface.co/ntua-slp/CultureMERT-95M) on non-Western datasets, while surpassing it on *Lyra* and Western benchmarks. It also outperforms [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) on Western tasks (MTAT and FMA-medium) by an average margin of **+0.7%** across all metrics.
 
 ---