Did full refresh and cleared Cache (Tested Others Browser) Same Result
Any idea why do I get this error when updating on nuc?
Thank you very much for implementing
Yeah, I made a mistake with picotts. I’ll push an update today with a fix, or you can switch to “nanotts” in your profile.
You’re welcome
Thank you very much for the new version. I want to try DeepSpeech, but unfortunately the download (german) doesn’t work.
The error is in the update process.
I can’t update on nuc from 2.5.8 to 2.5.9.
OK, I’ve made a small update to 2.5.9 with a fix for the picotts
problem.
You’re welcome
I haven’t been able to re-create this problem. Can you share your log, please?
[ERROR:2021-01-17 21:24:15,817] rhasspyserver_hermes: (‘https://raw.githubusercontent.com/synesthesiam/synesthesiam/de_deepspeech-aashishag/7aadb0561d37ada67c9353cf943eb66f06ec6636/model/alphabet.txt’, ‘File size mismatch (got 14 byte(s), expected 339)’)
Traceback (most recent call last):
File “/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/quart/app.py”, line 1821, in full_dispatch_request
result = await self.dispatch_request(request_context)
File “/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/quart/app.py”, line 1869, in dispatch_request
return await handler(**request_.view_args)
File “/usr/lib/rhasspy/rhasspy-server-hermes/rhasspyserver_hermes/main.py”, line 673, in api_download_profile
ssl_context=ssl_context,
File “/usr/lib/rhasspy/rhasspy-profile/rhasspyprofile/download.py”, line 494, in download_files
f"File size mismatch (got {final_size} byte(s), expected {bytes_expected})",
rhasspyprofile.download.DownloadFailedException: (‘https://raw.githubusercontent.com/synesthesiam/synesthesiam/de_deepspeech-aashishag/7aadb0561d37ada67c9353cf943eb66f06ec6636/model/alphabet.txt’, ‘File size mismatch (got 14 byte(s), expected 339)’)
[ERROR:2021-01-17 21:24:15,816] rhasspyprofile.download: Download failure (https://raw.githubusercontent.com/synesthesiam/synesthesiam/de_deepspeech-aashishag/7aadb0561d37ada67c9353cf943eb66f06ec6636/model/alphabet.txt, got 14 byte(s), expected 339)
[DEBUG:2021-01-17 21:24:15,552] rhasspyprofile.download: Downloading https://raw.githubusercontent.com/synesthesiam/synesthesiam/de_deepspeech-aashishag/7aadb0561d37ada67c9353cf943eb66f06ec6636/model/alphabet.txt to /profiles/de/deepspeech/model/0.9/alphabet.txt
Hi @Thargor, can you make sure your download.url_base
in your profile is set to "https://raw.githubusercontent.com/"
It looks like an extra synesthesiam/
is being added to the URL.
Yes you are right - now it is working. But I am pretty sure, that I didn’t touch anything in the profile …
Thank you very much!
Hey!
Thanks to the update. a lot of cool stuff in there and the new raven interface looks awesome.
I am still kinda new to rhasspy, coming from Snips. I started everything from 2.5.8 so this is my first update I have to roll out. I am using four rpi0-satellites and a base. Rolling out a new update is kinda painful (each sat takes about 20-30 minutes) so I thought if there is a simple update script I can put on every pi and trigger it somehow. Is something like this possible?
Seems another awesome update !
Will update and check all that. Of course my testing will be background music oriented !!
Hi
Does the deb package for 2.5.9 support Ubuntu 20.10? There seems to be a dependency on llvm-7-runtime when I try to install it, but Ubuntu 20.10 only has llvm-8-runtime and above.
There was mention of creating appImages when 2.5.8 was released, are these available yet ?
Kind regards
Dom
I’ll see if I can bump to LLVM 8 without breaking anything. Not sure why Ubuntu dropped 7.
Not officially yet, no. What hardware are you running Rhasspy on?
Hi.
I’m using home assistant and have rhasspy installed as add-on. I received the notification of rhasppy 2.9 and updated my addon. But still on the webpage (on :12101) the old version 2.5.7 (for some reason I have not made the update to 2.5.8) is showing up.
I checked the docker image version and it seems to be correct
3fbb1a43/amd64-addon-rhasspy 2.5.9 ed36febeb00e 29 hours ago 1.64GB
and also the container uses the correct image:
243d60d029ae 3fbb1a43/amd64-addon-rhasspy:2.5.9 “/run.sh” 29 hours ago Up 29 hours 0.0.0.0:12101->12101/tcp, 0.0.0.0:12333->12333/udp addon_3fbb1a43_rhasspy
I already tried uninstalling the addon and installing it again, but still 2.5.7 is in the header (of course I also made a refresh without cache)
am I missing something for the update? or does anybody has a hint want I can try in addition?
Regards,
Stefan
I tried DeepSpeach (german) instead of Kaldi in my Server Satellite Environment (both running the official docker container), but can’t geht it to work. It doesn’t seem to react. If I switch back to Kaldi, everything work again. I will try it again …
In my installation there are two lines “Satellite siteIds:…” for DeepSpeach. Is that a bug?
I am having the same experience. When using German Deepspeech my Server simply gives back a TimeOut. Same behaviour as I had on 2.5.8.
Anyone have info on how to use current_energy_threshold, max_current_energy_ratio_threshold, and max_energy? Are these helpful in silence detection?
I’m hoping they will be, but I’m not really an audio guy so I’m just going off of what I’ve read. To make use of these for silence detection, you will need to get the audio statistics working in the Rhasspy web UI or get the rhasspy-silence command-line tool running.
Here’s a brief overview for everyone:
- Audio “energy” is computed right here. This was borrowed from the speech_recognition library.
-
current_energy_threshold
just means that the energy of an audio chunk is compared to some threshold and, if it’s lower, the audio chunk is considered silence. -
max_current_energy_ratio_threshold
means that a ratio is computed for every audio chunk (max / current), and the chunk is considered silence if the value is above the threshold.- To make it intuitive, imagine the threshold ratio is 1. This means that if the current energy is ever less than the max energy, we have silence (
max/current > 1
). If we halve the threshold to 0.5, it means that anything quieter than half the max will be silence. - You can set
max_energy
to a specific value or let Rhasspy dynamically set it over time.
- To make it intuitive, imagine the threshold ratio is 1. This means that if the current energy is ever less than the max energy, we have silence (
Hope this helps some.
I have been wondering for a while if a neural network VAD would be a better option if the KWS was provided inhouse.
A considerable amount of the load is the conversion of audio to a MFCC image and a streaming model KWS just splits the images into ‘strides’ of 20msec or more.
I have been thinking a neural VAD could work on the strides and pass to KWS without any additional MFCC processing and the model would be quite lite due to only working on a stride at a time.
I am thinking a more accurate VAD could be provided with little more overhead than current could even be less as those strides would already be used by a KWS.
Haven’t looked in ages but the VAD currently has very similar FFT routines to the MFCC of some KWS and at times it isn’t great at judging what silence is.
If a VAD was trained with users voice then its likely it could be extremely accurate at detecting when the user is speaking or not which is probably a better metric than what we consider silence.