Reference pre-trained embedder models in Task Library documentation
PiperOrigin-RevId: 447830671
diff --git a/tensorflow/lite/g3doc/inference_with_metadata/task_library/image_searcher.md b/tensorflow/lite/g3doc/inference_with_metadata/task_library/image_searcher.md
index dac3dd7..74b9ee5 100644
--- a/tensorflow/lite/g3doc/inference_with_metadata/task_library/image_searcher.md
+++ b/tensorflow/lite/g3doc/inference_with_metadata/task_library/image_searcher.md
@@ -30,12 +30,14 @@
Before using the `ImageSearcher` API, an index needs to be built based on the
custom corpus of images to search into. This can be achieved using
-[Model Maker](https://www.tensorflow.org/lite/guide/model_maker).
+[Model Maker ImageSearcher API](https://www.tensorflow.org/lite/api_docs/python/tflite_model_maker/searcher).
For this you will need:
* a TFLite image embedder model such as
- [mobilenet v3](https://tfhub.dev/google/lite-model/imagenet/mobilenet_v3_small_100_224/feature_vector/5/metadata/1),
+ [mobilenet v3](https://tfhub.dev/google/lite-model/imagenet/mobilenet_v3_small_100_224/feature_vector/5/metadata/1).
+ See more pretrained embedder models (a.k.a feature vector models) from the
+ [Google Image Modules collection on TensorFlow Hub](https://tfhub.dev/google/collections/image/1).
* your corpus of images.
After this step, you should have a standalone TFLite searcher model (e.g.
diff --git a/tensorflow/lite/g3doc/inference_with_metadata/task_library/text_searcher.md b/tensorflow/lite/g3doc/inference_with_metadata/task_library/text_searcher.md
index 2ef1e64..faa7ad2 100644
--- a/tensorflow/lite/g3doc/inference_with_metadata/task_library/text_searcher.md
+++ b/tensorflow/lite/g3doc/inference_with_metadata/task_library/text_searcher.md
@@ -31,13 +31,21 @@
Before using the `TextSearcher` API, an index needs to be built based on the
custom corpus of text to search into. This can be achieved using
-[Model Maker](https://www.tensorflow.org/lite/guide/model_maker).
+[Model Maker TextSearcher API](https://www.tensorflow.org/lite/tutorials/model_maker_text_searcher).
For this you will need:
-* a TFLite text embedder model such as the
- [universal sentence encoder](https://tfhub.dev/google/lite-model/universal-sentence-encoder-qa-ondevice/1)
- model,
+* a TFLite text embedder model, such as the Universal Sentence Encoder. For
+ example,
+ * the
+ [one](https://storage.googleapis.com/download.tensorflow.org/models/tflite_support/searcher/text_to_image_blogpost/text_embedder.tflite)
+ retrained in this
+ [Colab](https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/examples/colab/on_device_text_to_image_search_tflite.ipynb),
+ which is optimized for on-device inference. It takes only 6ms to query a
+ text string on Pixel 6.
+ * the
+ [quantized](https://tfhub.dev/google/lite-model/universal-sentence-encoder-qa-ondevice/1)
+ one, which is smaller than the above but takes 38ms for each embedding.
* your corpus of text.
After this step, you should have a standalone TFLite searcher model (e.g.
