Sentence Similarity
PyTorch
sentence-transformers
multimodal
embeddings
retrieval
image-text
audio-text
text-image-audio
tri-encoder
semantic-router
Eval Results (legacy)
Instructions to use vllm-sr/multi-modal-embed-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use vllm-sr/multi-modal-embed-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("vllm-sr/multi-modal-embed-large") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download audio_0_WhisperEncoderTransformer/processor_config.json from vllm-sr/multi-modal-embed-large: direct link, hf CLI and curl.
- Browser
- Download file 409 Bytes
-
https://huggingface.co/vllm-sr/multi-modal-embed-large/resolve/refs%2Fpr%2F1/audio_0_WhisperEncoderTransformer/processor_config.json
- Command line
-
hf download hf://vllm-sr/multi-modal-embed-large@refs/pr/1/audio_0_WhisperEncoderTransformer/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/vllm-sr/multi-modal-embed-large/resolve/refs%2Fpr%2F1/audio_0_WhisperEncoderTransformer/processor_config.json
409 Bytes
| { | |
| "feature_extractor": { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| }, | |
| "processor_class": "WhisperProcessor" | |
| } | |