# hmmlearn/hmmlearn

Hidden Markov Models in Python, with scikit-learn like API

Repository: https://github.com/hmmlearn/hmmlearn
Canonical: https://ross.abutalabs.com/products/hmmlearn
Homepage: http://hmmlearn.readthedocs.org
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2024-10-31T09:14:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4546, "days_push": 671, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3416, forks 757 (observed 2026-08-28T04:08:03.717438+00:00)

## What it is
hmmlearn is a Python library providing algorithms for unsupervised learning and inference of Hidden Markov Models, with an API modeled on scikit-learn. It is now in limited-maintenance mode.

## Use cases
- fit hidden markov models to sequence data in python
- unsupervised learning of HMM parameters
- predict hidden states for time series
- scikit-learn style API for HMMs
- model sequential data with Gaussian or categorical emissions
- segment time series into hidden regimes

## When to choose
- you need HMM training and inference in Python with a familiar scikit-learn-like fit/predict API
- you want unsupervised estimation of HMM parameters from observation sequences

## When to avoid
- you need supervised HMM learning (use seqlearn instead)
- you need actively developed features or rapid bug fixes, since the project is in limited-maintenance mode
- you need modern sequence models like RNNs or transformers

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-science
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: hidden-markov-models, scikit-learn, time-series, unsupervised-learning, sequence-modeling, algorithms

## Member repositories
- hmmlearn/hmmlearn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:03.717438+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 2026-08-29T18:38:15.660783+00:00, confidence not recorded.
  - readme: https://github.com/hmmlearn/hmmlearn (fetched 2026-08-28T04:08:03.717438+00:00, sha 1ebb355e4d53)
  - registry_pypi: https://pypi.org/pypi/hmmlearn/json (fetched 2026-08-29T09:32:59.703228+00:00, sha 4b9d00b76006)
- Data as of 2026-08-30T08:39:29.467469+00:00.