{talkr} is an R package that offers a set of convenience functions for quality control, visualisation and analysis of conversational data. Most notably it provides a range of plotting functions that play well with ggplot and the tidyverse.
talkr offers a set of convenience functions for quality control, visualisation and analysis of conversational data.
It provides support for at least two common needs of people working with conversational corpora:
(1) quality control by offering rapid insights into the nature, timing, and quality of time-aligned annotations in a conversational corpus; and
(2) compelling visualisations by offering a range of plotting functions that play well with ggplot and the tidyverse.
Note: talkr plays well with its companion python package scikit-talk, which is focused more on processing conversational data and readying it for downstream analysis.
This package is available on CRAN and can be installed in R with
install.packages("talkr")
Development continues on GitHub, and you can install the development version of talkr with:
# install.packages("devtools")
devtools::install_github("elpaco-escience/talkr", build_vignettes = TRUE)
Two workflows for talkr are described in the workflows vignette.
You can also access the vignette from RStudio, by running:
vignette("workflows", package = "talkr")
Questions? Comments? They are more than welcome! This package is under active development and still has some rough edges. Interact with us in the issues if you have any questions or suggestions.
Diversity-aware language technology for conversational data
Scikit-talk is an open-source toolkit for processing collections of real-world conversational speech in Python. The toolkit aims to facilitate the exploration of large collections of transcriptions and annotations of conversational interaction.