--- license: apache-2.0 library_name: litert pipeline_tag: sentence-similarity language: - en tags: - mediapipe - litert - tflite - sentence-similarity - on-device - android - ios - web - python - flutter - nlp - sentence-embeddings - universal-sentence-encoder - dual-encoder - fp32 --- # MediaPipe Universal Sentence Encoder (Text Embedder) Compact dual-encoder text embedding model (`universal_sentence_encoder.tflite`, 6.1 MB, FP32) mapping text inputs to **100-dimensional** dense semantic vectors for rapid on-device cosine similarity and topical clustering in the [MediaPipe Text Embedder (`TextEmbedder`)](https://developers.google.com/edge/mediapipe/solutions/text/text_embedder) task.

Documentation: MediaPipe Text Embedder Docs

Samples: Android · iOS · Python Colab · Web · Flutter

Try live: Web Demo

Uses a compact dual-encoder architecture trained on question-answer datasets (`[-1, 100]` output vector). Captures topical similarity rather than sentiment polarity (for example, `"I like my phone"` and `"I hate my phone"` produce high similarity because both concern phones). ## Files | File | Precision | Size | SHA-256 | |---|---|---:|---| | [`universal_sentence_encoder.tflite`](https://huggingface.co/litert-community/MediaPipe-TextEmbedder-Universal-Sentence-Encoder/blob/main/universal_sentence_encoder.tflite) | `float32` | 6.12 MB (6,120,274 B) | `89ad3c74175dd8caa398cc22b657296d94302d20c525c12b58b29420f7249749` | ### Download ```bash pip install -U huggingface_hub hf download litert-community/MediaPipe-TextEmbedder-Universal-Sentence-Encoder universal_sentence_encoder.tflite --local-dir . ``` ## Inputs, Outputs, and Model Specifications ### `universal_sentence_encoder.tflite` - Embedded `TFLITE_METADATA`: name `USE-QA TFLite model` · version `1` · author `MediaPipe` | Direction | Tensor | Shape | Type | Notes | |---|---|---|---|---| | Input | `ParseExample/ParseExampleV2:1` | `[-1]` | `string` | inp_text — Input query text | | Input | `ParseExample/ParseExampleV2:2` | `[-1]` | `string` | res_context — Input query text | | Input | `ParseExample/ParseExampleV2:3` | `[-1]` | `string` | res_text — Input query text | | Output | `Final/EncodeQuery/mul` | `[-1, 100]` | `float32` | query_encoding — query-response similarity. | | Output | `Final/EncodeResult/mul` | `[-1, 100]` | `float32` | response_encoding — query-response similarity. | ## Use with MediaPipe Tasks ### Python Quickstart ```bash pip install -U mediapipe huggingface_hub ``` ```python import mediapipe as mp from huggingface_hub import hf_hub_download model_path = hf_hub_download(repo_id="litert-community/MediaPipe-TextEmbedder-Universal-Sentence-Encoder", filename="universal_sentence_encoder.tflite") BaseOptions = mp.tasks.BaseOptions TextEmbedder = mp.tasks.text.TextEmbedder TextEmbedderOptions = mp.tasks.text.TextEmbedderOptions options = TextEmbedderOptions(base_options=BaseOptions(model_asset_path=model_path), quantize=True) with TextEmbedder.create_from_options(options) as embedder: e1 = embedder.embed("It's a charming and affecting journey.").embeddings[0] e2 = embedder.embed("What a great and fantastic trip!").embeddings[0] print("Cosine similarity:", TextEmbedder.cosine_similarity(e1, e2)) ``` ### Cross-Platform Guides & Samples - **Task overview & options:** [Text Embedder documentation](https://developers.google.com/edge/mediapipe/solutions/text/text_embedder) - **Platform setup guides:** [Python](https://developers.google.com/edge/mediapipe/solutions/setup_python) · [Web / JavaScript](https://developers.google.com/edge/mediapipe/solutions/setup_web) · [Android (Kotlin / Java)](https://developers.google.com/edge/mediapipe/solutions/setup_android) · [iOS (Swift)](https://developers.google.com/edge/mediapipe/solutions/setup_ios) · [Flutter (Dart)](https://developers.google.com/edge/mediapipe/solutions/setup_flutter) - **Runnable sample apps:** [Web Demo](https://google-ai-edge.github.io/mediapipe-samples-web/#/text/text_embedder) · [Web Source](https://github.com/google-ai-edge/mediapipe-samples-web/blob/main/src/tasks/text-embedder.ts) · [Android](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/text_embedder/android) · [iOS](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/text_embedder/ios) · [Python Notebook](https://colab.research.google.com/github/google-ai-edge/mediapipe-samples/blob/main/examples/text_embedder/python/text_embedder.ipynb) · [Flutter](https://github.com/google/flutter-mediapipe/tree/main/samples/text/text_embedder) ## Latency Benchmarks Average CPU pipeline latency reported by the [Text Embedder documentation](https://developers.google.com/edge/mediapipe/solutions/text/text_embedder#benchmarks): | Model Variant | Device | CPU Latency | |---|---|---:| | Universal Sentence Encoder | Galaxy S26 Ultra (4 threads) | 10 ms | ## Intended Use, Limitations, and Fairness - **Intended applications:** Lightweight on-device semantic similarity, FAQ/retrieval matching, and topical grouping where minimal size (6.1 MB) and ≈10 ms CPU latency are prioritized over 768D LLM embeddings. - **Limitations & considerations:** Dual-encoder trained on QA pairs; for multilingual or instruction-steered retrieval/classification tasks, consider `MediaPipe-TextEmbedder-EmbeddingGemma-300M`. No standalone Google fairness PDF is published for this model on the MediaPipe documentation page. ## Provenance Every model binary in this repository is byte-identical (unmodified FlatBuffer weights and embedded `TFLITE_METADATA` bytes) to the official artifact served by Google from `storage.googleapis.com/mediapipe-models`. | Repo File | Upstream URL | GCS Generation | Upstream `Last-Modified` | Pinned Bucket Version | |---|---|---|---|---| | `universal_sentence_encoder.tflite` | [`universal_sentence_encoder.tflite`](https://storage.googleapis.com/mediapipe-models/text_embedder/universal_sentence_encoder/float32/latest/universal_sentence_encoder.tflite) | `1682480025114200` | Wed, 26 Apr 2023 03:33:45 GMT | `/1/` | ## License and Citation - License: `apache-2.0` — Distributed under Apache License, Version 2.0 alongside the [MediaPipe](https://github.com/google-ai-edge/mediapipe) release artifacts. ### Citation Architecture linked from the MediaPipe Text Embedder documentation: [`aclanthology.org/2022.emnlp-main.640.pdf`](https://aclanthology.org/2022.emnlp-main.640.pdf).