Skip to content

k2 integration #283

@bonham79

Description

@bonham79

https://github.com/k2-fsa/k2

Recently played around with the above. Really fast construction of FSAs on GPU. Given that a lot of our models use monotonic assumptions, having access to lattice constructions with autograd would give us some cool novel architectures for our set of tasks.

Some extensions we can have:

  1. Push monotonic transducer and edit action transducers to use trainable lattices
  2. Allow integration of our models with language n-grams. This can improve training by preventing illegal constructions not seen in training data.
  3. Helps with creation of CTC/Transducer models for NLP tasks.

N.B. From a self-serving route. Little birdy told me this wasn't getting much love these days, so want to keep it around the OpenGRM/Pynini/Thrax family to keep it alive. (Implementing GPU based FSA algorithms would be nifty masters project for CUNY peeps.)

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Type

No type
No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions