 |
Archive ouverte en Sciences de l'Homme et de la Société |
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
Abstract : This paper reports on progress integrating the speech recognition toolkit ESPnet into Elpis, a web front-end originally designed to provide access to the Kaldi automatic speech recognition toolkit. The goal of this work is to make end-to-end speech recognition models available to language workers via a user-friendly graphical interface. Encouraging results are reported on (i) development of an ESPnet recipe for use in Elpis, with preliminary results on data sets previously used for training acoustic models with the Persephone toolkit along with a new data set that had not previously been used in speech recognition, and (ii) incorporating ESPnet into Elpis along with UI enhancements and a CUDA-supported Dockerfile.
https://halshs.archives-ouvertes.fr/halshs-03030529
Contributor : Alexis Michaud <>
Submitted on : Tuesday, February 23, 2021 - 4:14:35 PM
Last modification on : Wednesday, February 24, 2021 - 4:04:38 PM
Contributor : Alexis Michaud <>
Submitted on : Tuesday, February 23, 2021 - 4:14:35 PM
Last modification on : Wednesday, February 24, 2021 - 4:04:38 PM
Files
Licence
Distributed under a Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License