Most inference engines support embedding models for text, images, and video, but almost none support audio embedding models. To generate audio embeddings, we typically need to use Python with PyTorch, or convert the model to ONNX and run it with ONNX runtime. There has been no out-of-the-box solution.

In Build Recommender System with LLM-based Reranker, we explored turning a user’s past interests into a query and using a reranker to rank candidate items. With the emergence of decision models such as Jev, recommender systems have another option: treat “Will this user like this item?” as a judgment task and rank items directly by the probabilities returned by the decision model.

In 2025, we benchmarked the performance of text embedding models in similarity-based recommendations. Within six months of that benchmark's publication, Alibaba Cloud and Google launched a new generation of open-source text embedding models: qwen3-embedding by Alibaba Cloud and embeddinggemma by Google. Recently, the gorse-bench tool also added benchmark features for text embedding models. In this post, we use gorse-bench and the playground dataset to conduct a comprehensive evaluation of popular open-source text embedding models.