@HatkeshiatorTND क्लांकरनोइज़ इज़ नॉट गुड ऑन द ईयर्स
0
0
0
@HatkeshiatorTND लुक ईस्पीक साउण्डस लाईक शिट ऍण्ड गिव्स मी अ हॆडेख़
1
0
1
@HatkeshiatorTND सी इट्स सो मच बॆट्टर नाउ प्लस दे कैन्नॉट ईवन रीड दिस अन्लॆस दे मेक ऍन ऎफ़र्ट।
(देवा इज़ जस्ट अ मोर फ़ोर्मल गुज्जू लिपी सो इट चेक्स आउट)
(देवा इज़ जस्ट अ मोर फ़ोर्मल गुज्जू लिपी सो इट चेक्स आउट)
0
0
1
@HatkeshiatorTND
eh local models are good enough that it sounds alright enough, I use tts because stupid sensory issues make reading a pain so I tend to skip lines + adhd making me go zoomie so I sometimes just prefer a tts which makes it easier to stay on line and makes reading a more relaxing activity
Also since when are arabs become clankers?
eh local models are good enough that it sounds alright enough, I use tts because stupid sensory issues make reading a pain so I tend to skip lines + adhd making me go zoomie so I sometimes just prefer a tts which makes it easier to stay on line and makes reading a more relaxing activity
Also since when are arabs become clankers?
2
0
1
meeper
meeper
jai janendra from today onwards, english shall be written in the gujarati script
0
0
1
@HatkeshiatorTND I'm using sherpatts on android, I don't want a clanker voice speakinng to me but something that sounds like a human being.
Piper on loonicks supports espeak ipa symbols but apparenlty not sherpatts (which uses the same models tho)
Also for whatever reasonn speechd STILL doesn't natively support pipertts which is stupid, and the jugaad they suggest basically involve running a shell script each time, which makes it reload the model mulltiple times, instead of idk like running piper tts server and using an api + a reaper process.
It shouldn't be that hard and somebody should have made that in all these years, it woud even be possible in fucking bash
Piper on loonicks supports espeak ipa symbols but apparenlty not sherpatts (which uses the same models tho)
Also for whatever reasonn speechd STILL doesn't natively support pipertts which is stupid, and the jugaad they suggest basically involve running a shell script each time, which makes it reload the model mulltiple times, instead of idk like running piper tts server and using an api + a reaper process.
It shouldn't be that hard and somebody should have made that in all these years, it woud even be possible in fucking bash
1
0
1
meeper
meeper
Why is english orthograpy so fucking shit, tryinng to use regex replacement for tts, and desperately trying to make it not pronounce g as j or not use syllable ending e as a vriddhi marker for the previous vowel (ie like how the e in shite, makes the i sound long)
Also that read is not differenciated with read (past tense) even though they have completely different pronunciations for fucking fuck's sake.
Also sherpatts apparently doesn't support ipa :blobcatpunishedandflayed:
if only anglo used devanagri or whatever
Also that read is not differenciated with read (past tense) even though they have completely different pronunciations for fucking fuck's sake.
Also sherpatts apparently doesn't support ipa :blobcatpunishedandflayed:
if only anglo used devanagri or whatever
1
0
1
meeper
repeated
repeated
1
0
1
2
0
0
meeper
meeper
1
0
0