SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.10384 · 2023

Powerful and Extensible WFST Framework for RNN-Transducer Losses

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper presents a framework based on Weighted Finite-State Transducers (WFST) to simplify the development of modifications for RNN-Transducer (RNN-T) loss. Existing implementations of RNN-T use CUDA-related code, which is hard to extend and debug. WFSTs are easy to construct and extend, and allow debugging through visualization. We introduce two WFST-powered RNN-T implementations: (1) "Compose-Transducer", based on a composition of the WFST graphs from acoustic and textual schema -- computationally competitive and easy to modify; (2) "Grid-Transducer", which constructs the lattice directly for further computations -- most compact, and computationally efficient. We illustrate the ease of extensibility through introduction of a new W-Transducer loss -- the adaptation of the Connectionist Temporal Classification with Wild Cards. W-Transducer (W-RNNT) consistently outperforms the standard RNN-T in a weakly-supervised data setup with missing parts of transcriptions at the beginning and end of utterances. All RNN-T losses are implemented with the k2 framework and are available in the NeMo toolkit.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.10384")
get_code_for_paper("2303.10384")
have("2303.10384")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.10384.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.10384.svg)](https://syntology.ai/paper/2303.10384)

Connect an agent — have() is free.