This is example scripts in the open source Kaldi toolkit for building a speech recognition for french language
The speech corpus is a corpus of French read speech. We collected the data from the LibriVox project. It is available for download for free at https://mega.nz/#F!oMp3xAqY!7fiwn30szuTpIDy6eLhJcw. It was prepared as a speech recognition corpus for training and evaluation using KALDI ASR toolkit.