Feature Extraction
Transformers
Safetensors
audio_embeddings
audio
custom_code
self-supervised-learning
audio-embeddings
best-rq-2
audioset
Instructions to use ltuncay/BEST-RQ-2.2-base-2M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ltuncay/BEST-RQ-2.2-base-2M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ltuncay/BEST-RQ-2.2-base-2M", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ltuncay/BEST-RQ-2.2-base-2M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download export_manifest.json from ltuncay/BEST-RQ-2.2-base-2M: direct link, hf CLI and curl.
- Browser
- Download file 2.7 kB
-
https://huggingface.co/ltuncay/BEST-RQ-2.2-base-2M/resolve/main/export_manifest.json
- Command line
-
hf download hf://ltuncay/BEST-RQ-2.2-base-2M/export_manifest.json
-
curl -L -o export_manifest.json https://huggingface.co/ltuncay/BEST-RQ-2.2-base-2M/resolve/main/export_manifest.json
2.7 kB
| { | |
| "schema_version": 1, | |
| "model_name": "BEST-RQ-2.2-base-2M", | |
| "mock": false, | |
| "model_target": "src.models.best_rq22_module.BestRQ22Module", | |
| "source": { | |
| "checkpoint_sha256": "a0dbb85c931c5576445aec6c4f8afe4a02f071b21237a1440372398c7ffcb51d", | |
| "global_step": 2000000, | |
| "wandb_run": { | |
| "path": "tuncay-ludovic/audio embeddings/sq96rg53", | |
| "name": "best-rq-2-2-hmlp_audioset_2m_128x2bs_mask0.8_bf16-mixed", | |
| "checkpoint_name": "checkpoints/last.safetensors" | |
| }, | |
| "training_config_sha256": "337bbf98fc4886c557b80a4f1bb06cc44c4df0cbf03d8591b4140926c684ccbd", | |
| "configured_max_steps": 2000000 | |
| }, | |
| "runtime_versions": { | |
| "torch": "2.9.1", | |
| "torchaudio": "2.9.1", | |
| "transformers": "5.17.0", | |
| "timm": "1.0.22", | |
| "einops": "0.8.1" | |
| }, | |
| "validation": { | |
| "max_absolute_error": 0.0, | |
| "batch_size": 2 | |
| }, | |
| "files": { | |
| "CODE_LICENSE": "8fe9e8b749cd4abedabcb3100df445db899e72192394d14cc2dbf24a40811af6", | |
| "LICENSE": "8fe9e8b749cd4abedabcb3100df445db899e72192394d14cc2dbf24a40811af6", | |
| "README.md": "ca49f24d50f19c79524ad8fb386c626cdeced51e0532c1be1fbe39e47ce8deca", | |
| "adapters.py": "ca0f26826763c0e48b7508da732242bb83adfeb4814e389ed3fde93ad648c728", | |
| "config.json": "93452b1dfb678bafd2737b29cc80586e1ccd8368ad0183ed3b88ffd8f12ed6f2", | |
| "configuration_audio.py": "59f3a0b8db0df5af85e677ac33a4431595e9b2eff6d34c1e6a1778dd75a4568d", | |
| "evaluation_results.json": "dbe52acb66d358cf0313121a18c917a1b2e37068df0ccadb0c7a8a6d4b806a14", | |
| "extraction.py": "8949389abc52278e24634518f72eae1270bb1a649ad016b71e0d6e8113acaa7c", | |
| "feature_extraction_audio.py": "5ed9004727be8b61bd6c0efbeb703b634c20c1b790d9fd59d6a9910438e89b39", | |
| "model.safetensors": "e0daf13449c77fe1d720df9990e6372e7bd98a64a9834785f13680f9182ccdb1", | |
| "modeling_audio.py": "ba394cd7f80929274090bc1b8986298247f61494db5ed99c0c5469f4e30bb874", | |
| "normalization.py": "918b0eb9d547e77ba1adc154deb33d29861532e2a0cd7663497bfc9df6155cef", | |
| "patch_embed.py": "825cf2ca0a9d8d10e12f40dc69d2293aabf04b627b926d42314a8b5193e231f7", | |
| "preprocessor_config.json": "e37df5cada8190b709335e4c7d45e714617cfcdd532d0e270562225b173b26af", | |
| "requirements.txt": "08c9ad278bc06a31d7c7ed3a2255dca48bd63faf29ae7c27635c284d082bb818", | |
| "rope.py": "d74bdc7a7dd4ba98414f93c4f1937b95614b57394984d265af5999327efc2d82", | |
| "spectrogram.py": "b1e6de8e8ec8220ad9369a765f80a1504b13a6a54aae2ab5bc18cd8dd1e0a894", | |
| "transformer.py": "03ea1cb7509669f91003f8cd94edd3660b0c6788e14335ca995c60834a2017d4", | |
| "vit.py": "cb6b05b5f617def68e05c40e6bf4d8a24a7b43e5acc4481649e3541bd172e727", | |
| "waveform_feature_encoder.py": "69c811624650441e7f46d4fc4e8177c9bac2f65970aef5c6fbd826522f109e22" | |
| } | |
| } | |