|
Configuration and test:
On Ubuntu Dapper.
First Attempt:
$ festival
Festival Speech Synthesis System 1.4.3:release Jan 2003
Copyright (C) University of Edinburgh, 1996-2003. All rights reserved.
For details type `(festival_warranty)'
festival> (print (mapcar (lambda (pair) (car pair)) voice-locations))
(en1_mbrola kal_diphone ked_diphone rab_diphone don_diphone us1_mbrola el_diphone)
nil
festival> (SayText "Where is the money")
#
festival> (voice_us1_mbrola)
us1_mbrola
festival> (SayText "Where is the money")
Binary number format error
You are probably using a version of /usr/share/festival/voices/english/us1_mbrola/us1/us1 incompatible
with your machine architecture.
Get the right one from the MBROLA project homepage :
http://tcts.fpms.ac.be/synthesis
Cannot open file /tmp/est_07467_00000.au as tokenstream
Wave load: can't open file "/tmp/est_07467_00000.au"
Cannot load wavefile: /tmp/est_07467_00000.au
#Utterance 0xb72563d8
festival> (quit)
Second Attempt:
$ festival
Festival Speech Synthesis System 1.4.3:release Jan 2003
Copyright (C) University of Edinburgh, 1996-2003. All rights reserved.
For details type `(festival_warranty)'
festival> (print (mapcar (lambda (pair) (car pair)) voice-locations))
(en1_mbrola kal_diphone ked_diphone rab_diphone don_diphone us1_mbrola el_diphone)
nil
festival> (SayText "Where is the money")
#
festival> (voice_us1_mbrola)
us1_mbrola
festival> (SayText "Where is the money")
#Utterance 0xb72913d8
festival> (quit)
|