How to use from the
Use from the
LiteRT library
# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

MediaPipe Text Classifier (Average Word Embedding)

On-device English sentiment classification model (average_word_classifier.tflite, 776 KB) trained on Stanford Sentiment Treebank (SST-2) movie reviews for the MediaPipe Text Classifier (TextClassifier) task.

Documentation: MediaPipe Text Classifier Docs

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

Try live: Web Demo

Ultra-fast continuous bag-of-words / average word-embedding classifier (776 KB, FP32, [−1, 256] input) trained on SST-2 (0 = negative, 1 = positive), embedding a 10,003-entry regex vocab.txt (<PAD>, <START>, <UNKNOWN>, plus vocabulary words) and labels.txt inside TFLITE_METADATA.

Files

File Precision Size SHA-256
average_word_classifier.tflite float32 775.7 KB (775,706 B) 13bf6f7f35964f1e85d6cc762ee7b1952009b532b233baa5bdb4bf7441097f34

Download

pip install -U huggingface_hub
hf download litert-community/MediaPipe-TextClassifier-AverageWord average_word_classifier.tflite --local-dir .

Inputs, Outputs, and Model Specifications

average_word_classifier.tflite

  • Embedded TFLITE_METADATA: name TextClassifier · version 1 · author MediaPipe · packed associated files: vocab.txt, labels.txt
Direction Tensor Shape Type Notes
Input serving_default_input_1:0 [-1, 256] int32 input_text — Embedding vectors representing the input text to be processed.
Output StatefulPartitionedCall:0 [-1, 2] float32 score — Score of the labels respectively. — Labels: labels.txt

Use with MediaPipe Tasks

Python Quickstart

pip install -U mediapipe huggingface_hub
import mediapipe as mp
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="litert-community/MediaPipe-TextClassifier-AverageWord", filename="average_word_classifier.tflite")

BaseOptions = mp.tasks.BaseOptions
TextClassifier = mp.tasks.text.TextClassifier
TextClassifierOptions = mp.tasks.text.TextClassifierOptions

options = TextClassifierOptions(base_options=BaseOptions(model_asset_path=model_path))
with TextClassifier.create_from_options(options) as classifier:
    result = classifier.classify("An unforgettable and genuinely moving film!")
    for cat in result.classifications[0].categories:
        print(f"{cat.category_name}: {cat.score:.3f}")

Cross-Platform Guides & Samples

Latency Benchmarks

End-to-end MediaPipe Task pipeline average latency reported by the Text Classifier documentation:

Model Variant Device CPU Latency GPU Latency
Average Word Embedding Pixel 6 0.14 ms —

Intended Use, Limitations, and Fairness

  • Intended applications: Binary English sentiment analysis (positive vs. negative) on short text snippets such as reviews and feedback.
  • Out-of-scope & limitations:
    • English only: Not suitable for non-English text.
    • Domain shift: Trained on SST-2 movie reviews (https://nlp.stanford.edu/sentiment/index.html); accuracy may degrade on unrelated domains, sarcasm, or multi-sentence documents.
    • 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
average_word_classifier.tflite average_word_classifier.tflite 1682480023219908 Wed, 26 Apr 2023 03:33:43 GMT /1/

License and Citation

  • License: apache-2.0 — Distributed under Apache License, Version 2.0 alongside the MediaPipe release artifacts.
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including litert-community/MediaPipe-TextClassifier-AverageWord