The phoneset for the new voice is defined in the script mbarnig_en_marco_phoneset.scm. The file ws_nf in the mbarnig_en_marco/etc folder is automatically generated by WaveSurfer. The file fs in the mbarnig_en_marco/etc folder contains the following parameters : FV_INST=mbarnigįV_VOICENAME=$FV_INST"_"$FV_LANG"_"$FV_NAME The spaces after the left parantheses are required. The prompt list is coded in the standard Festival data-format. These 3 sentences contain each of the english phonemes once. ( uniph_0003 "you should fetch azure mike." ) The file uniphone.data in the mbarnig_en_marco/etc folder contains the following minimal prompt-set : ( uniph_0001 "a whole joy was reaping." ) The following scripts are created inside the 7th folder ( mbarnig_en_marco/festvox) : The following sub-folders (most empty) are created inside the 6th folder ( mbarnig_en_marco/festival) : The following files are created inside the 4th folder ( mbarnig_en_marco/etc) : The following programs are copied into the 1sr folder ( mbarnig_en_marco/bin) : The following folders are created inside the voice directory mbarnig_en_marco : The arguments of the setup script setup_clunits are : To construct the voice folder structure and copy there the template files for voice building. I launched the script $FESTVOXDIR/src/unitsel/setup_clunits mbarnig en marco uniphone Voice Folderįirst I created a new voice folder mbarnig_en_marco inside the Festival_TTS/festvox/ directory and opened a terminal window inside this new folder. festival> (SayText "Hello Marco, how are you?") 1.festival> (voice_mbarnig_en_marco_clunits).(copy data in Festival voice directory).festival -b festvox/build_clunits.scm '(build_clunits.festival -b festvox/build_clunits.scm '(build_utts.(uncomment the line USE_SOX=1 in the script prompt_them).festival -b festvox/build_clunits.scm '(build_prompts_waves.$FESTVOXDIR/src/unitsel/setup_clunits mbarnig en marco uniphone.(creation of the voice directory mbarnig_en_marco).The list of the different steps is shown below : The goal is to set up my system to create a luxembourgish synthetic voice for the Festival package. Referring to my recent post about Festival, I am glad to announce that I was successful in building and testing a new uniphone voice (english) with my own prompt recordings.
0 kommentar(er)
