Feature Extraction
Transformers
Safetensors
mert2
audio
music
music-understanding
representation-learning
custom_code
Instructions to use m-a-p/MERT-v2-FullSong with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use m-a-p/MERT-v2-FullSong with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="m-a-p/MERT-v2-FullSong", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("m-a-p/MERT-v2-FullSong", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from m-a-p/MERT-v2-FullSong: direct link, hf CLI and curl.
- Browser
- Download file 215 Bytes
-
https://huggingface.co/m-a-p/MERT-v2-FullSong/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://m-a-p/MERT-v2-FullSong/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/m-a-p/MERT-v2-FullSong/resolve/main/preprocessor_config.json
215 Bytes
| { | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "sampling_rate": 24000, | |
| "padding_value": 0.0, | |
| "padding_side": "right", | |
| "return_attention_mask": true, | |
| "do_normalize": false | |
| } | |