k2
gtn
k2 | gtn | |
---|---|---|
2 | 2 | |
1,046 | 112 | |
1.5% | 0.0% | |
7.1 | 1.8 | |
3 days ago | about 2 years ago | |
Cuda | C++ | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
k2
-
Differentiable Finite State Machines
This 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).
-
What are some good speech recognition papers I can implement?
k2
gtn
-
Differentiable Finite State Machines
FB research has their own version of automatic differentiation of WFSTs: https://github.com/gtn-org/gtn
See also https://github.com/facebookresearch/gtn_applications which contains examples of applications such as handwriting recognition and speech recognition.
- Automatic differentiation with weighted finite-state transducers
What are some alternatives?
espnet - End-to-End Speech Processing Toolkit
TerpreT
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
gtn_applications - Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"