# Bad quality of text embeddings with MediaPipe **URL:** \ **Category:** Google AI Edge\ **Tags:** text, models\ **Created:** [July 29, 2025, 2:16pm UTC](https://discuss.ai.google.dev/t/bad-quality-of-text-embeddings-with-mediapipe/96013 "2025-07-29T14:16:31Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![Lake6985](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/lake6985/32/25569_2.png) [@Lake6985](https://discuss.ai.google.dev/u/Lake6985)\ **Post date:** [July 29, 2025, 2:16pm UTC](https://discuss.ai.google.dev/t/bad-quality-of-text-embeddings-with-mediapipe/96013/1 "2025-07-29T14:16:31Z")
Hi all Today , I have tried the Media Pipe for the first time. My goal is to compute cosinus similarities between a text query and a set of FAQ entries. The corpus is a French corpus and contains some industrial technical terms (mainly acronyms & abbreviations) I am a little bit disappointed with the results. The accuracy/precision is 0.18 and MRR 0.26 I made some experimentations with the model ‘embedder.tflite’ . I also tried ‘universal\_sentence\_encoder.tflite’ but resultats are not better. Is there any other model that I can try with MediaPipe to generate my embeddings and to get better results ? Outside the ecosystem of Media Pipe, I used all-MiniLM-L6-v2 / multilingual-e5. Results are very good but the quantization and porting the tokenizer on Android (my target) is not very easy. ---
**Author:** ![Joel\_Sathiyendra](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/joel_sathiyendra/32/1800_2.png) [@Joel\_Sathiyendra](https://discuss.ai.google.dev/u/Joel_Sathiyendra)\ **Post date:** [July 30, 2025, 4:45am UTC](https://discuss.ai.google.dev/t/bad-quality-of-text-embeddings-with-mediapipe/96013/3 "2025-07-30T04:45:52Z")
Hi @Lake6985 , The model accuracy is expected to be low. MediaPipe solutions are for edge devices, and they are benchmarked with run times on CPUs. If anyone has a different view on this, please let me know. As you said, performance increases with model size. However, I checked the all-MiniLM-L6-v2/multilingual-e5, and they have a TensorFlow model. You can convert it to TFLite and use it. ---
**Author:** ![Lake6985](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/lake6985/32/25569_2.png) [@Lake6985](https://discuss.ai.google.dev/u/Lake6985)\ **Post date:** [July 30, 2025, 6:10am UTC](https://discuss.ai.google.dev/t/bad-quality-of-text-embeddings-with-mediapipe/96013/4 "2025-07-30T06:10:43Z")
Hi Joel Thank you for your prompt response. I perfectly understand that performances on edge device are the priority. In my work, I mainly target edge devices for our application and it is a tough work. As you suggest, I will investigate in converting the all-MiniLM-L6-v2 to TFLite in order to be able to use it with media pipe. But what about the tokenisation? I can export the config files (\*.json files) and the model of the tokenizer (sentencepiece.bpe.model) but how to build a sentence piece tokenizer from files with Media Pipe ? Is there any way to use the SentencePeice tokenizer of Google with MediaPipe? coud you please tell me if you see any way to do that ? I really hope I will be able to use Media Pipe to build my FAQ . Thx ---
**Author:** ![Maisie\_Leblanc](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/maisie_leblanc/32/55257_2.png) [@Maisie\_Leblanc](https://discuss.ai.google.dev/u/Maisie_Leblanc)\ **Post date:** [August 12, 2025, 1:39pm UTC](https://discuss.ai.google.dev/t/bad-quality-of-text-embeddings-with-mediapipe/96013/6 "2025-08-12T13:39:37Z")
What is MediaPipe…? I have never heard of it before! ---
**Author:** ![Lake6985](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/lake6985/32/25569_2.png) [@Lake6985](https://discuss.ai.google.dev/u/Lake6985)\ **Post date:** [August 27, 2025, 11:29am UTC](https://discuss.ai.google.dev/t/bad-quality-of-text-embeddings-with-mediapipe/96013/8 "2025-08-27T11:29:05Z")
sorry for the delay @Maisie_Leblanc you can find information about MediaPipe here: [MediaPipe Solutions guide  |  Google AI Edge  |  Google AI for Developers](https://ai.google.dev/edge/mediapipe/solutions/guide)