license: cc-by-nc-4.0
tags:
- audio
- music
metrics:
- roc_auc
- average_precision
- f1
model_type: audio-classification
pipeline_tag: audio-classification
library_name: transformers
CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
📑 Read the full paper (to be presented at ISMIR 2025)
CultureMERT-95M is a multi-culturally adapted 95M-parameter music foundation model based on MERT-v1-95M. It is developed through a two-stage continual pre-training (CPT) strategy on 650 hours of culturally diverse audio spanning Greek, Turkish, and Indian musical traditions. The model significantly improves representation quality for "non-Western" music, achieving an average ROC-AUC improvement of +4.43% across culturally diverse music tagging tasks, surpassing prior state-of-the-art, while maintaining strong performance on Western-centric benchmarks such as MagnaTagATune and FMA-medium.
🔀 Alternative variant available: CultureMERT-TA-95M is a merged model constructed via task arithmetic, combining separately adapted models—each continually pre-trained (using the same two-stage CPT strategy) on data from a single musical tradition.
🧠 Model Details
- Architecture: 12-layer Transformer encoder (768-dim) with a 7-layer 1D CNN frontend
- Input: Raw mono audio at 24kHz
- Training Context Length: 5 seconds
- Pretraining Objective: MLM-style multi-task masked prediction of discrete EnCodec acoustic tokens and continuous constant-Q transform (CQT) spectrogram reconstruction at a 75 Hz feature rate
🌍 Training Data
| Dataset | Music Tradition | Hours Used |
|---|---|---|
| Lyra | Greek traditional/folk | 50h |
| Turkish-makam | Turkish/Ottoman classical | 200h |
| Hindustani | North Indian classical | 200h |
| Carnatic | South Indian classical | 200h |
- To further stabilize adaptation and mitigate catastrophic forgetting, we include 20% Western data (20 hours from Music4All) during Stage 1 of continual pre-training.
🔒 The datasets used were obtained under research-use agreements and are not redistributed.
📊 Evaluation
We evaluate CultureMERT-95M via probing on both Western and non-Western automatic music tagging tasks. All results are averaged over five random seeds. Metrics used:
- ROC-AUC (Area Under the Receiver-Operating Characteristic Curve)
- mAP (Mean Average Precision)
- Micro-F1 and Macro-F1
Evaluation follows the MARBLE protocol under constrained settings. We use standardized train/test splits from ccml for continual pre-training and probing-based evaluation.
Evaluation Datasets and Metadata Used (Top-k Tags)
- Non-Western traditions:
- Turkish-makam: Top-30 tags, covering "makam", "usul", and "instruments"
- Hindustani: Top-20 tags, primarily reflecting "raga", "tala", "instruments", and "forms"
- Carnatic: Top-20 tags, primarily reflecting "raga", "tala", "instruments", and "forms"
- Lyra: Top-30 tags, related to "genre", regional ("place"), and "instruments" metadata
- Western benchmarks:
- MagnaTagATune (MTAT): Top-50 tags, spanning "genre", "instruments", and "mood"
- FMA-medium: Top-20 hierarchical "genre" tags
Top-k tags were selected based on tag frequency distributions.
The evaluation results are shown in the following tables:
ROC-AUC / mAP
| Model | Turkish-makam | Hindustani | Carnatic | Lyra | FMA-medium | MTAT | Avg. |
|---|---|---|---|---|---|---|---|
| MERT-v1-95M | 83.2% / 53.3% | 82.4% / 52.9% | 74.9% / 39.7% | 85.7% / 56.5% | 90.7% / 48.1% | 89.6% / 35.9% | 66.1% |
| CultureMERT-95M | 89.6% / 60.6% | 88.2% / 63.5% | 79.2% / 43.1% | 86.9% / 56.7% | 90.7% / 48.1% | 89.4% / 35.9% | 69.3% |
Micro-F1 / Macro-F1
| Model | Turkish-makam | Hindustani | Carnatic | Lyra | FMA-medium | MTAT | Avg. |
|---|---|---|---|---|---|---|---|
| MERT-v1-95M | 73.0% / 38.9% | 71.1% / 33.2% | 80.1% / 30.0% | 72.4% / 42.6% | 57.0% / 36.9% | 35.7% / 21.2% | 49.3% |
| CultureMERT-95M | 77.4% / 45.8% | 77.8% / 50.4% | 82.7% / 32.5% | 73.1% / 43.1% | 58.3% / 36.6% | 35.6% / 22.9% | 52.9% |
📈 CultureMERT-95M outperforms the original MERT-v1-95M by an average of +4.43% in ROC-AUC across non-Western traditions, with consistent improvements of +5.4% in mAP, +3.6% in Micro-F1, and +6.8% in Macro-F1, while exhibiting minimal forgetting on Western datasets.
🔧 Model Usage
from transformers import Wav2Vec2FeatureExtractor, AutoModel
import torch
from torch import nn
import torchaudio.transforms as T
from datasets import load_dataset
# Load model weights and preprocessor config
model = AutoModel.from_pretrained("ntua-slp/CultureMERT-95M", trust_remote_code=True)
processor = Wav2Vec2FeatureExtractor.from_pretrained("ntua-slp/CultureMERT-95M", trust_remote_code=True)
# Load example audio
dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation", trust_remote_code=True).sort("id")
audio_array = dataset[0]["audio"]["array"]
sampling_rate = dataset.features["audio"].sampling_rate
# Resample if needed
resample_rate = processor.sampling_rate
if resample_rate != sampling_rate:
print(f'Setting sample rate from {sampling_rate} to {resample_rate}')
resampler = T.Resample(sampling_rate, resample_rate)
else:
resampler = None
# Audio file is decoded on the fly
if resampler is None:
input_audio = dataset[0]["audio"]["array"]
else:
input_audio = resampler(torch.from_numpy(dataset[0]["audio"]["array"]).to(dtype=resampler.kernel.dtype))
# Extract hidden states
inputs = processor(input_audio, sampling_rate=resample_rate, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs, output_hidden_states=True)
# Representations: 13 layers (CNN feature extractor + 12 Transformer)
# NOTE: each layer performs differently in different downstream tasks - you should choose empirically
all_layer_hidden_states = torch.stack(outputs.hidden_states).squeeze()
print(all_layer_hidden_states.shape) # [13 layer, Time steps, 768 feature_dim]
# For utterance-level classification tasks, you can simply reduce the representation in time
time_reduced_hidden_states = all_layer_hidden_states.mean(-2)
print(time_reduced_hidden_states.shape) # [13, 768]
# You can even use a learnable weighted average representation over all layers
aggregator = nn.Conv1d(in_channels=13, out_channels=1, kernel_size=1)
weighted_avg_hidden_states = aggregator(time_reduced_hidden_states.unsqueeze(0)).squeeze()
print(weighted_avg_hidden_states.shape) # [768]
Ethical Considerations
This model is released under a non-commercial CC BY-NC 4.0 license and is intended for research purposes. While it is designed to address cultural bias in MIR, its training data and pretraining paradigm may still reflect cultural and dataset-specific biases. The model should not be used in commercial or generative applications without explicit consideration of cultural representation, proper attribution, and consent from relevant communities and dataset curators.
📚 Citation
...TODO