pollen-robotics/dtw

Health v2 · maintenance only

Adoption not part of the score

1230 stars · 236 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A small Python module implementing Dynamic Time Warping (DTW), a similarity measure between temporal sequences. It offers a basic pure-Python/NumPy implementation plus an accelerated version using scipy's cdist, with utilities to visualize accumulated cost matrices and alignment paths.

Use cases

• compare similarity between two time series sequences
• simple speech recognition with DTW and MFCC features
• measure distance between audio signals for sound matching
• align and match gesture or motion sensor data
• visualize DTW cost matrix and optimal warping path
• compute DTW distance between numpy arrays

When to choose

• you need a lightweight, easy-to-use DTW implementation in Python with numpy/scipy
• you want to visualize accumulated cost matrices and warping paths
• you're doing simple template-based speech or audio comparison
• your sequences are small enough that a basic DTW implementation suffices

When to avoid

• you need highly optimized or GPU-accelerated DTW for very long sequences
• you need advanced DTW variants like subsequence DTW, derivative DTW, or soft-DTW
• you need a maintained library with recent Python version support (tested only up to Python 3.6)
• you need DTW integrated into a larger machine-learning pipeline with gradient support

Facets

library · maturity maintenance

math machine-learning audio-processing machine-learning speech-processing data-science python cross-platform dynamic-time-warping similarity-measure numpy scipy time-series algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="pollen-robotics/dtw")