# mesolitica/NLP-Models-Tensorflow

Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0

Repository: https://github.com/mesolitica/NLP-Models-Tensorflow
Canonical: https://ross.abutalabs.com/products/nlp-models-tensorflow
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: nlp, machine-learning, deep-learning, lstm, attention, lstm-seq2seq-tf, neural-machine-translation, optical-character-recognition, dnc-seq2seq, pos-tagging, summarization, embedded, luong-api, chatbot, speech-to-text, language-detection
Archived: true
Last push: 2020-07-20T09:04:56+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3054, "days_push": 2235, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1781, forks 712 (observed 2026-08-28T04:05:35.565262+00:00)

## What it is
A collection of 335+ simplified Jupyter Notebook implementations of machine learning and TensorFlow 1.x deep learning models for NLP tasks, covering summarization, translation, chatbots, OCR, speech-to-text, tagging, and more. It is designed as a beginner-friendly, research-oriented reference rather than a production library.

## Use cases
- learn seq2seq and attention models for NLP
- find simplified TensorFlow implementations of NLP papers
- build a chatbot with LSTM seq2seq
- implement neural machine translation from scratch
- study OCR and speech-to-text model implementations
- learn text classification and summarization models
- explore POS tagging and entity tagging notebooks

## When to choose
- you want readable, notebook-style reference implementations of NLP models
- you are still on TensorFlow 1.13–1.x
- you need examples of many different NLP task architectures in one place
- you want to adapt research paper implementations for your own experiments

## When to avoid
- you use TensorFlow 2.x or PyTorch
- you need a production-ready, maintained NLP library
- you want pip-installable, versioned APIs rather than notebooks
- you need up-to-date transformer-based implementations

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: nlp, machine-learning, deep-learning, speech-recognition, tts, ocr, chatbot, data-visualization
- domain: machine-learning, deep-learning, speech-processing, tutorials
- platform: python, cross-platform
- tags: tensorflow, jupyter-notebooks, seq2seq, attention, lstm, neural-machine-translation, summarization, pos-tagging, text-classification, educational, natural-language-processing, gpu

## Member repositories
- mesolitica/NLP-Models-Tensorflow (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:35.565262+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:24:25.086305+00:00, confidence not recorded.
  - readme: https://github.com/mesolitica/NLP-Models-Tensorflow (fetched 2026-08-28T04:05:35.565262+00:00, sha c66c4b5c4560)
- Data as of 2026-08-30T08:39:29.467469+00:00.