WOwoodson·Feb 7, 2025
There’s also k2 (https://github.com/k2-fsa/k2) which implements a lot of FSA and FST algorithms in CUDA, with PyTorch bindings.
In Show HN: Transductive regular expressions for text editingk2-fsa
k2
Cuda2022–2025
k2-fsa / k2
k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
2Distinct people
2Mentions
0Explicit recommenders
1.4KGitHub stars
What to know before exploring
What it is
FSA/FST algorithms, differentiable, with PyTorch compatibility.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year2 dated mentions
Observed mentions: 2022-06-08 19:45:20 UTC to 2025-02-07 23:06:16 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 0 | 0 | 0 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 0 | 0 | 0 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
2 sourcesThis uses dense (soft/weighted) transitions from any state to any state, and then some regularization to guide it to more sparse solutions.
In practice, the number of states can be huge (thousands, maybe millions), so representing this as a dense matrix (a 1Mx1M matrix is way too big) is not going to work. It must be sparse, and in practice (all FST you usually deal with) it is. So it's very much a waste to represent it as a dense matrix.
That's why there are many specialized libraries to deal with FSTs. Also in combination with deep learning tools. See e.g. K2 (https://github.com/k2-fsa/k2).
In Differentiable Finite State Machines