Feature Extraction
Transformers
Safetensors
PerceptionEncoder
English
pe_audio_video
audio-text-retrieval
image-text-retrieval
zero-shot-audio-classification
multimodal-embeddings
Eval Results (legacy)
Instructions to use MC7ever/pe-single-L14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MC7ever/pe-single-L14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="MC7ever/pe-single-L14")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("MC7ever/pe-single-L14") model = AutoModel.from_pretrained("MC7ever/pe-single-L14", device_map="auto") - PerceptionEncoder
How to use MC7ever/pe-single-L14 with PerceptionEncoder:
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("MC7ever/pe-single-L14", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from MC7ever/pe-single-L14: direct link, hf CLI and curl.
- Browser
- Download file 850 Bytes
-
https://huggingface.co/MC7ever/pe-single-L14/resolve/main/processor_config.json
- Command line
-
hf download hf://MC7ever/pe-single-L14/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/MC7ever/pe-single-L14/resolve/main/processor_config.json
850 Bytes
| { | |
| "feature_extractor": { | |
| "feature_extractor_type": "PeAudioFeatureExtractor", | |
| "feature_size": 1, | |
| "hop_length": 1920, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 48000 | |
| }, | |
| "processor_class": "PeAudioVideoProcessor", | |
| "video_processor": { | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": false, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "height": 336, | |
| "width": 336 | |
| }, | |
| "video_processor_type": "PeVideoVideoProcessor" | |
| } | |
| } | |