Skip to content

Deepspeech/Coqui AI speech to text systems in Esperanto. - Parolrekoniloj en Esperanto uzante Deepspeech/Coqui Ai.

Notifications You must be signed in to change notification settings

parolteknologio/stt-esperanto

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

73 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Esperanto STT

Using deepspeech/coqui ai and the common voice dataset

Tools/Iloj

eblaj datumfontoj

Datumaro versio grandeco permesilo
Common Voice CV Corpus 7.0 17 GB 748 h CC 0
tatoeba 03.06.20 4 063 audio files CC-BY
lingualibre 03.06.20 425 MB CC BY-SA

experiments so far

datumaro parametroj GPU rezultoj
eo_41h_2019-12-10 ? 2 x 1080 Ti 32Gb RAM (leadertelecom) WER 0.5
eo_844h_2021-07-21 english checkpoints, n_depth 2048, dropout_rate 0.3, learning_rate 0.0001 details Google Colab Pro Plus WER 24,7% (test was part of train dataset) download

Vosk Model

There is an Esperanto Vosk Model that can be used in many tools such as Kdenlive to create subtitles: https://alphacephei.com/vosk/models

To do:

About

Deepspeech/Coqui AI speech to text systems in Esperanto. - Parolrekoniloj en Esperanto uzante Deepspeech/Coqui Ai.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published