STRUNK
-
Posts
569 -
Joined
-
Last visited
-
Days Won
19
Posts posted by STRUNK
-
-
On 10/20/2024 at 7:44 PM, datiswous said:
Actually I see the ai-voice-cloning repo what the video is about also lists a Linux install.
I have to try Docker sometime.
There is a new TTS : https://github.com/SWivid/F5-TTS
Should be a lot better with "emotion". -
20 hours ago, datiswous said:
Yeah that's for Windows though, but nice to see you get it working
I think it can run on ios and linux but that might not be as simple as the window install:
https://github.com/neonbjb/tortoise-tts
https://git.ecker.tech/lightmare/tortoise-tts -
-
-
-
Ik got this tortoise TTS up and running after some hassle and made a model for Builder1.
Builder one has just 4 audiofiles and I ran 500 epochs on it, what might be way too much for such a small sample size, and the model is about 1.6Gb, but it seems to work quite nicely.
Some outputs sounded a bit strange and for most of them I had to cut of the start of the audiofile for there was some garbage.
I still have to play around with settings but for now it's looking (sounding) quite nice.
To install it I followed this tutorial, though some things differ a bit when you install version 3 that came after this tutorial:He is using some other programs to remove background noise and to prepare the audio, but the voices in TDM are already clean so no need for that. What you will have to do is convert all the ogg files to wav (batch convert with vlc player) for tortoise TTS to be able to handle them.
You also need an Nvidia graphics card.
That said, on my rtx5000 laptop GPU it all takes a lot of time ...
-
1
-
-
Npc density is off the charts!!
REEEE : P-
1
-
-
6 hours ago, datiswous said:
Yeah I saw it, but the demo page is not able to generate a voice from audio file. The WhisperSpeech demo does have this ability. I tested this and it does generate a pretty realistic voice, it's not really a copy of the voice you supply. Also if the supplied voice has a heavy accent it makes mistakes.
I tried that yesterday and I thought it sounded pretty bad : P
The thing is, there must also be a way to steer the speech output, and train voice sets of the dfferent npc's; bored, angry, alarmed etc. to be really usefull .. I guess. Like training LoRa's for image generation ...
I'll try to install and use tortoise TTS this weekend. -
4 hours ago, datiswous said:
This seems pretty good:
I was looking at this one yesterday:
https://github.com/neonbjb/tortoise-tts
6 hours ago, nbohr1more said:See:
Thanx.
So I see voice actors don't like it and some other people neither.
My idea came when I locked out a guard on a balcony and thought; would be nice is he was yelling some
about being stuck on the balcony in his normal guard voice.
Maybe I/we just have to try what the quality of speech generation is these days.
But .. is there any copyright on these "in game" npc voices? -
I think it would be quite a handy tool to have an AI that can generate dialog in the voices that are already included, and even the various voice actors, if they are ok with that ...
and have it run local on your own computer.
Any thoughts on that? -
This looks very good and lots of ways to go about. I enjoyed it a lot.
SpoilerI locked out the guard in te mansion by placing some chairs in front of the balcony door when he was up there : P
-
1
-
-
1 hour ago, Wallace said:
Great mission, though can anyone help me out with the Soul Jar puzzle? I read the note and activated the lamps in what I believed were the right order, but the jar remains locked in its cage. It pains me to ask for help, but I'm out of ideas.
SpoilerThe "cage" should open and you should be able to grab the soul jar ... if you light them in the right sequence.
Ice = an ice cristal, left from where you enter on ground level.
Earth=a vine, in the middle on ground level.
Cup = a cup, middel right (seen from there you enter), 1st level.
Death = a skull, left of the "cage".-
1
-
-
Jack, you are a true master!!
This was just epic ...-
1
-
-
29 minutes ago, huntaffer said:
I am playing on Linux, Intel core5, GTX 1650, which is not a weak GPU, but low midrange at least.
FPS is dropping from 60 to ~30 in some areas and its annoying.
Any optimization possible ?
As TDM versions evolve, the more this game becomes slower.
The game is looking a lot better through the years and yes, it needs more processing power to look that way. But, for me it doesn't get too slow in any way, and I'm still playing on a 2011 HP Z800 with a gtx 1660, almost on the highest settings.
BUT, I didn't play through the whole game yet and some missions in the past had massive FPS drops for me in some areas. Those have been solved however by by reporting them as detailed as possible : )
TDM is just awsome I think, even if it's not always perfect .. and it's free!!!
This mission by Jack, that has cost him (and others) countless months of work, if not years in total (regarding the learning process), is the newest example of that. It looks so good that I'm playing it as slow as possible, just because I want to "be there" : P
-
13 hours ago, ecbert said:
how to get inside
SpoilerThrough the side door, you have to use the chef's special lockpick.
-
1
-
-
On 4/7/2024 at 9:42 PM, kingsal said:
The room is suppose to be inaccessible, I think you got up somewhere I didn't intent for players to get to
.
Well ...
Spoilerthere are these movable white bales, and I, very legitimately, using other bales to build a stack, managed to take one onto the "wall" and placed it under the window. I could then just climb in and was sad there was no secret to be found : (
-
YeeY, I succeeded the 45 second challenge!!
It's not hard at all : P
I'm not telling how ofc : )
SpoilerBut you have to make sure you have a running start .. ^^
Also, I like these "little" missions with extra challenges, like the quite common "secrets" (only found one so far) .. and a very rare "time challenge" only added to my enjoyment!
All of you "april fools missions" contributors: it was a real treat!
-
On 4/6/2024 at 11:24 PM, SeriousToni said:
It seems to be ai generated if I'm not mistaking. Sometimes the people have six fingers, sometimes the eyes are strange, sometimes the text is gibberish. But if it is done well I guess it's a comfortable way to enhance your mission intros.
Very nice little mission BTW I really enjoyed it! Loved the rat secret.
Well, it looks very good!
I tried generating some textures with AI, and it look quite good but the free model(s) lost the option to generate images and I'm too cheap to pay for it : P -
Nice menu : P
The intro is grandious!! Who draw these? -
Very enjoyable little mission, I liked evereythig about it!
You should team up with Amadeus!! : P-
1
-
-
Still enjoying the missions you guys make : )
-
2
-
-
Somehow your missions play out in a scenery that invites me to just hang around and enjoy.
I was almost 4 hours in this mission, just because is was a nice place to be : )
-
1
-
-
Oh great Jedi!! Thanx for the mission. I found the fireflies already : )
Now for the rest of the mission ..-
1
-
-
@datiswous
Could you share your .map file here?
How about AI voice generation using the already existing voices?
in TDM Editors Guild
Posted
The cloning of the characteristics of the voice works quite nice.
I selected sets of audio clips by how "loud" the speech is, Loud, Normal and Soft (speaking up, speaking normal, speaking soft).
I didn't figure out how to get the best audio quality, without weird "audio artifacts".
But as demonstrated down here, the moor certainly sounds like the moor: