# baidu-research/warp-ctc

Fast parallel CTC.

Repository: https://github.com/baidu-research/warp-ctc
Canonical: https://ross.abutalabs.com/products/warp-ctc
Language: Cuda
License: Apache-2.0
License Family: permissive
Last push: 2024-03-04T07:10:15+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": 3884, "days_push": 912, "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 4069, forks 1025 (observed 2026-08-28T04:08:34.198384+00:00)

## What it is
A fast parallel implementation of the Connectionist Temporal Classification (CTC) loss function for CPU and CUDA GPU, with a simple C interface and Torch bindings. It is designed for training sequence models such as end-to-end speech recognition systems without needing input-label alignments.

## Use cases
- compute CTC loss for training speech recognition models
- train end-to-end sequence models without frame-level alignments
- speed up CTC computation on GPU for large-scale training
- integrate a fast CTC loss into a custom deep learning framework via the C API
- keep training data on GPU to maximize data parallelism

## When to choose
- you need a numerically stable, high-performance CTC loss on CPU or NVIDIA GPU
- you are training recurrent or end-to-end speech recognition models at scale
- you want a C interface to embed CTC into your own training stack

## When to avoid
- you need bindings for modern frameworks like PyTorch or TensorFlow (built-in CTC may suffice)
- your project requires actively maintained dependencies or recent GPU architectures
- you are not training sequence models that need CTC

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, gpu-computing
- domain: deep-learning, speech-processing, machine-learning
- platform: windows, cpp
- tags: ctc-loss, speech-recognition, sequence-learning, torch-bindings, cuda, linux, macos, gpu

## Member repositories
- baidu-research/warp-ctc (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.198384+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 2026-08-29T18:23:31.267198+00:00, confidence not recorded.
  - readme: https://github.com/baidu-research/warp-ctc (fetched 2026-08-28T04:08:34.198384+00:00, sha 4a589e722f69)
- Data as of 2026-08-30T08:39:29.467469+00:00.