A grapheme to phoneme (G2P) tool for Spanish
A grapheme to phoneme (G2P) tool for Spanish.
To use it, simply:
- Just for one time:
cd g2p_spanish && chmod -R 744 ./* - Create a UTF-8 file with one word per line:
nano original.txt ./doPron.sh original.txt lexicon 1
The final file will be encoded in UTF-8 lexicon.pron.
Note: the third parameter takes into account the differences in áéíóúÁÉÍÓÚ for the phonemes (value=1). Otherwise you can just keep value=0.
Requires
Python2, Linux
Credits
- Transcriptor ortofonético: Andres Marzal, Maria Jose Castro, Salvador España and Ismael Salvador
- Source codebase: César González Ferreras
Contact
Cristian Tejedor-García
Email: cristian [dot] tejedorgarcia [at] ru [dot] nl
GitHub