Festival: Difference between revisions

From XPUB & Lens-Based wiki
(New page: Open-source text to speech project. <source lang="bash"> text2wave <<O | mplayer -cache 8192 - All electrical and mechanical systems here are now under my control. O </source>)
 
No edit summary
 
(4 intermediate revisions by 2 users not shown)
Line 1: Line 1:
Open-source text to speech project.
Open-source text to speech project http://www.cstr.ed.ac.uk/projects/festival/ .


<source lang="bash">
Festival can be used in at least 3 modes:
text2wave <<O | mplayer -cache 8192 -
=Festival modes=
All electrical and mechanical systems here are now under my control.
* interactive
O
$ festival
> (Say Text "Hello World")
* pipe from stdin
$ cat letter.txt | festival --tts
* saving to file
** text2wave - convert text to .wav files
** lame - converts .wav to mp3
$ cat letter.txt | text2wave | lame - file.mp3
* server
???????
 
 
=using different voices=
==diphone voices==
To installing the standard [http://www.festvox.org/ Festvox] diphone voices in Debain/Ubunto
$ apt-get cache search festvox*
$ apt-get install festvox-don festvox-rablpc16k festvox-kallpc16k festvox-kdlpc16k
 
Now that you have some diphone voices installed you can test them in intereactive mode
 
List existing voices
festival> (voice.list)
(cstr_us_awb_arctic_multisyn kal_diphone don_diphone)
 
Set a voice: Note '''voice_'''name_from_voice
  festival> (voice_cstr_us_awb_arctic_multisyn)
 
==MBROLA voices==
...
==CMU Arctic voices==
...
 
=Setting Festival defaults=
By creating and editing the file ~/.festivalrc you can change Festival default settings, such as 
the voice path - where it will be played; 
the voice used or volume and stretch. The following file provides a few example.
 
<nowiki>;;</nowiki> are comments
 
<source lang="text">
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;;; Basic voice/system configuration
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
;;;;;;;; Voice path
;;Voice path: sound card; Debian-specific: Use aplay to play audio
(Parameter.set 'Audio_Command "aplay -q -c 1 -t raw -f s16 -r $SR $FILE")
 
;; Voice path: mplayer -> jack
;;(Parameter.set 'Audio_Command "mplayer -ao jack:port=system -really-quiet -noconsolecontrols -nojoystick -nolirc -nomouseinput -demuxer rawaudio -rawaudio channels=1:rate=$SR $FILE") ;; to SYSTEM OUT via JACK
 
;;;;;;; The default voice
(set! voice_default voice_cmu_us_ksp_arctic_clunits) ;; Indian MALE
;;(set! voice_default voice_cmu_us_bdl_arctic_clunits) ;; US MALE
;;(set! voice_default voice_cmu_us_slt_arctic_clunits) ;; US FEMALE
;;(set! voice_default 'voice_cmu_us_awb_arctic_clunits) ;;
;;(set! voice_default 'voice_us2) ;;
 
 
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;;; Advanced voice configuration
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
;;;; Slow the standard voices down
(Parameter.set 'Duration_Stretch 0.5)
 
;;;; Set volume.
(set! default_after_synth_hooks
    (list (lambda (utt) (utt.wave.rescale utt 2.0 t))))
</source>
</source>
=links=
[https://wiki.archlinux.org/index.php/Festival Arch Linux manual on Festival HOWTO: Make festival TTS use better voices (MBROLA / CMU / HTS)]
[http://ubuntuforums.org/showthread.php?t=751169 HOWTO: Make festival TTS use better voices (MBROLA / CMU / HTS)]
[http://teknologisuara.blogspot.nl/2011/11/howto-make-festival-tts-use-better.html http://teknologisuara.blogspot.nl/2011/11/howto-make-festival-tts-use-better.html]
[http://ubuntuforums.org/showthread.php?t=677277 Howto: Setup more realistic voices in Festival.]

Latest revision as of 11:45, 20 April 2015

Open-source text to speech project http://www.cstr.ed.ac.uk/projects/festival/ .

Festival can be used in at least 3 modes:

Festival modes

  • interactive
$ festival
> (Say Text "Hello World")
  • pipe from stdin
$ cat letter.txt | festival --tts
  • saving to file
    • text2wave - convert text to .wav files
    • lame - converts .wav to mp3
$ cat letter.txt | text2wave | lame - file.mp3 
  • server
???????


using different voices

diphone voices

To installing the standard Festvox diphone voices in Debain/Ubunto

$ apt-get cache search festvox*
$ apt-get install festvox-don festvox-rablpc16k festvox-kallpc16k festvox-kdlpc16k

Now that you have some diphone voices installed you can test them in intereactive mode

List existing voices

festival> (voice.list)
(cstr_us_awb_arctic_multisyn kal_diphone don_diphone)

Set a voice: Note voice_name_from_voice

 festival> (voice_cstr_us_awb_arctic_multisyn)

MBROLA voices

...

CMU Arctic voices

...

Setting Festival defaults

By creating and editing the file ~/.festivalrc you can change Festival default settings, such as the voice path - where it will be played; the voice used or volume and stretch. The following file provides a few example.

;; are comments

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;;; Basic voice/system configuration
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;;;;;;;; Voice path
;;Voice path: sound card; Debian-specific: Use aplay to play audio 
(Parameter.set 'Audio_Command "aplay -q -c 1 -t raw -f s16 -r $SR $FILE")

;; Voice path: mplayer -> jack
;;(Parameter.set 'Audio_Command "mplayer -ao jack:port=system -really-quiet -noconsolecontrols -nojoystick -nolirc -nomouseinput -demuxer rawaudio -rawaudio channels=1:rate=$SR $FILE") ;; to SYSTEM OUT via JACK

;;;;;;; The default voice
(set! voice_default voice_cmu_us_ksp_arctic_clunits) ;; Indian MALE
;;(set! voice_default voice_cmu_us_bdl_arctic_clunits) ;; US MALE 
;;(set! voice_default voice_cmu_us_slt_arctic_clunits) ;; US FEMALE
;;(set! voice_default 'voice_cmu_us_awb_arctic_clunits) ;; 
;;(set! voice_default 'voice_us2) ;; 


;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;;; Advanced voice configuration
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;;;; Slow the standard voices down
(Parameter.set 'Duration_Stretch 0.5)

;;;; Set volume.
(set! default_after_synth_hooks
    (list (lambda (utt) (utt.wave.rescale utt 2.0 t))))




links

Arch Linux manual on Festival HOWTO: Make festival TTS use better voices (MBROLA / CMU / HTS)

HOWTO: Make festival TTS use better voices (MBROLA / CMU / HTS)

http://teknologisuara.blogspot.nl/2011/11/howto-make-festival-tts-use-better.html

Howto: Setup more realistic voices in Festival.