Just wondering when the 64 debs might be available.
No rush just curious 
1 Like
Working on it this week
2 Likes
is there a way to get the best of both options? i really like the exact match on my sentences but also want wildcard on the end of them like uh: define (word). I was able to get it to work with the last image but idk what to do now. in one of these patches i swear it was just perfect. It would get the sentences and any extra words I’d throw in. It would just send it in the raw text.
I actually do know how to do this now. I will need to extend the templating language with a “wildcard” symbol. Maybe just “*”?
If I use the same trick as the “unknown words”, then * would match any single word from the base dictionary. Unfortunately, multiple wildcards in a row would not be subject to the statistics of the base language model (so “the big dog” would be just as likely as “dog big the”).
Thoughts?
multiple words i dont need. that’s just too much. u need like cloud huge ai for that. I’m just looking for one word. Sometimes i’ll ask google a couple words to throw in its search engine too. Like i would just like the ability to choose at which point open transcription starts? Idk. I mean its pretty good at recognizing my sentences with fast speed too. If we want to throw random words in for questions though it just is all over the place. If i tweak the older version just open transcription with 0.3 confidence. It will half the time get what I’m saying i think. Idk how we could do it but unless there’s huge priority. We are really close to getting there. I know bash maybe i could help u out. Would have to look at the code base. I mean I’m pretty surprised how well i got it working considering its completely offline. New voices are a huge step forward btw. good job. sound a lot better. even if it takes an extra 2-3 seconds. On a raspberry pi 4 4gb
1 Like
Update
The Docker images have been updated, and the Debian packages for 2.5.11 are now available!
Changes are described below:
Unknown Words
Based on feedback, I’ve modified the “unknown words” feature for Kaldi. To reduce training time with it enabled, I now create a single “unknown sentence” path in the grammar. Speaking something outside your sentences.ini should produce something like <unk> <unk> ... up to a maximum number of words.
You can adjust the probability of the “unknown sentence” (default is 1e-5). If you end up with too many false positives for unknown words, try lowering the probability.
Cancel Word
The old version of “unknown words” didn’t work, but I realized it was perfect for a “cancel” word! So now in the Kaldi settings, you can set a special word that will immediately cancel the current voice command. Just make sure it’s not a word you’re using in your intents
So if you were to set the “cancel” word to “terminate”, you could say something like:
turn on the terminate
and Kaldi will return:
turn on the <unk>
which will cause fsticuffs to report a failed recognition. You can set the cancel word to whatever you like (I wouldn’t use a word from your intents), and change the probability.
8 Likes
I just pulled the new Docker Image.
Thanks for all the work.
Iam looking for the “cancel” word at Kaldi settings, but didnt found it. Are there some post tasks necessary to bring up the new features?
Btw.: Did you already add the german Voice “kerstin” to 2.5.11?
You’re welcome!
Did you pull the specific 2.5.11 version? I haven’t updated latest yet. Hopefully I didn’t mess something up. Either way, I’ll be pushing a new update in the next few days.
No, but I’m working on this today. There will be a total of 50 voices for Larynx now, thanks to volunteers
I actually have the same problem as @Enc3ph4l0n with my raspberry pi 4 (64bit). I will not enable the “unknown” functionality right now.
The problem I am facing, is that rhasspy sometimes wakes up and turn on/off the light, when I am watching TV.
For the wakeup, I am still trying to adjust snowboy settings; However, for the intent recognization, can you explain how to create a separate “catch all” intent?
With the new unknown words functionality, the “catch all” intent is effectively the “not recognized” message. In the Kaldi settings, there should be a "Replace unknown words with " checkbox that you can enable. There are a few other settings to tweak, the unknown words probability and max unknown words (max length of the “unknown” sentence).
When will the new update talked about in the august 20th post be available?
And when will the next “official” release be available, if it is only a preview released next time?
1 Like
Hi @WallyDW, I’ve released 2.5.11 via Docker and on Github. I haven’t made a post about it just yet, since I’m behind on some other stuff.
I will soon 
3 Likes
Quite OK. I know how real life can interfere with the important stuff.
It just sounded like the next release was around the corner. Guess, I have to round around corners some more.
1 Like
If you pull rhasspy/rhasspy via Docker or grab the latest Debian packages, it should all be there
Thanks alot.
I will take a look at it tomorrow.
Its a bit late here now
1 Like
@synesthesiam
I am playing around with the new version and slowly moving forward.
I will post my experiences here when I feel something is important.
For now I have discovered the following.
Something required libffi.so.6, but I am using Debian Bullseye and the libffi.so I had was a version 7.
I just made a symlink with “ln -s /usr/lib/x86_64-linux-gnu/libffi.so.7 /usr/lib/x86_64-linux-gnu/libffi.so.6”, which seems to have solved it.
On the configuration on Mozilla DeepSpeech there are two fields for satellite siteids. They seem to be connected, since changing one updates the other.
hmm, it seems that the siteid on the first page does not work.
I put in bedroom in the field on my central server and then tries to make it speak on the bedroom satellite, but the MQTT message state the siteid is central and not bedroom, so nothing comes out.
Multiple audio streams for Precise/Porcupine/Snowboy/Pocketsphinx wake word service (thanks Romkabouter)
I assume we still need multiple UDP ports for each satellite device? In Home Assistant I have the Rhasspy Addon, 2.5.11, but seems like one can only configure one UDP port 12333. How can I map several ports to the underlying container?
- Wake word systems can receive raw UDP audio from multiple sites, and forward it to MQTT (see wake…udp_site_info)
Can you share an example with multiple Site IDs? Seems like the UI doesn’t support this config.
Hi,
Been far from Rhasspy for a while. Seems no docker update from 3 months now.
What’s going on regarding Rhasspy development actually ? Any 2.5.12 in pipe ?
I didn’t had time to put my production setup on 2.5.11 yet so I will setup a new test pi before migrating. Just reading new stuff 
Sadly, this seems to be the future of Rhasspy:
https://community.rhasspy.org/t/the-future-of-rhasspy/3373/18