Some development has been done on BBB for the interpretation feature. If you want to try the beta version, you can sign up here : https://translation.meet-modular.com. I will try it this week or next week with our interpreters.
happy new year, Camille!
That’s interesting news indeed! I tried it but couldn’t figure out any changes in the user interface, but maybe I missed something. Let us know!
I think they took off the feaure yesterday afternoon. But it’s back again this morning. I hope I will have time to test it before they stop this try out. I have a meeting with my interpreters to test it next Monday!
Hi everyone,
I tried the new interpretation feature with 2 interpreters and here are my feedback that I shared on github : The system works quite well. It takes us a bit of time to understand it but then it was really smooth. Our only issue was the quality of the sound. In the floor we didn’t have any problem. The sound was good but when we were on the language channel, the sound was not good enough to understand well the interpreter. One of my interpreter told me that it can come from some technical adjustment to get a better sound on the line. An other issue was the delay of hearing the interpreter when it starts talking.
Just saw that now there is a code to add translation feature in BBB. I don’t know if it’s something possible for meet.coop. See below the last info I found.
A time consuming challenge was to guarantee good audio quality of the translation tracks, when translators use windows laptops, where we had problems with echo cancellation, the floor output was always disturbing the translators’ voice. This has been finally solved by disabling echo cancellation on the translator’s SIP channel make translation audio depend on main audio connection / echo test (#64) · Issues · chat / fairblue · GitLab
Some UX fine tuning and documentation works is ongoing and we do not have install scripts yet, but there are guides how to replace the HTML5 client, here is one of them Audio sharing · Wiki · hosting / fairteaching · GitLab
Creating a PR so that this function gets into the BBB core would be another larger task and would require some attention from the BBB maintainers. Please do not ask when this will happen. Releasing a stable BBB 2.3 version has priority in the next months. Meet the developers of the translation tool at this chat channel fairchat
The practical matter of translating and interpreting within a BBB session is the kind of thing that the emerging Community programme will want to engage with, in its toolstack thread. So I’m cross-posting this between the topics for future reference. Given that this topic is well established here, I’d say the discussion can safely rermain here under ‘Product’?
Hopefully soon we can have funds to work on incorporating these technical solutions, like Camille shows above in the thread. Until then we will need to continue with social workarounds, like Monica c.s. have documented. Now some of us are involved in the Cities for Change Forum that takes place partially at meet.coop servers. Some of the sessions are multilingual, so we have had a prep session with session organisers and translators.
Following our testing session yesterday, Silvia from Guerilla Media Collective (translators) has put together some practical instructions for simultaneous interpretation on BBB. In the end the document is a bit long, but in turn it has step-by-step instructions for both moderators and interpreters: Interpretation procedure for BBB meetings - Google Docs
Hello everyone, this is fascinating and impressive. I’ve been working as both a professional and volunteer interpreter for years and would love to plug into work around developing this feature for BBB. Is there any way to get involved in testing, brainstorming, etc for random people like me??
They refer to four approaches to multilanguage gatherings and map out a plan for running session#4 in commons.hour (led by femProcomuns) as a dual-language Spanish/English session. @camille might be interested, as well as @wouter@benjaminroyer and Cade (forgotten his Forum handle, oops!)?
Contributors in this thread may be interested in the discussion thread on commons.hour #9 Working in plural languages online Session#9 discussion - #3 by mikemh
It’s mostly a matter of meeting protocols. There isn’t any specific tech fix for simultaneous interpretation - like an interpreters’ control panel for example, as used in multilanguage conferences witth special audio equipment. Also we’re thinking about machine translation in various forms, but nothing specific on the roadmap I think @wouter ?
From many members in our community we know that multi-language is very much desired, and we are aware of the current difficulties. Still, as @otisyves, @fredsultan and Matthieu from Remix the Commons have explained so well in the last #commons.hour it depends very much on the social protocol how to go about this. But tech can be more helpful. Add also feedback from users in loud environments, like a general assembly or meetings in public spaces: automatic subtitling would be very practical.
Based on these user requests we do have “improved multi-language features” on our roadmap. It is however to be defined in more detail about what it is that we want, and then we should seek funding, possibly crowd-funding, for it.
I could imagine this automatic subtitling to be very useful and possibly also the most feasible. And possibly added to that automatic translation of these subtitles.
We’re probably not the first to attempt this, although I haven’t found public repositories under free licenses that we can reuse so far yet.
One speech-2-text tool that @mikemh pointed me to is nerd-dictation. Probably @baybars knows much much more of this domain. Would be good to explore this together.
Hey @wouter!
Just finished some quick tests with VOSK (VOSK Offline Speech Recognition API) - the Open Source library under nerd-dictation. I used few audio files from Remix collection. The results are quite impressive (in terms of accuracy - speakers from France and Morocco - I didn’t test with a French-Canadian speaking person…). The library seems to integrate well with other systems.
It doesn’t provide translation but a « live » transcription - a text (pretty rough one) that can be translated afterwards. That’s a start.
The prospect of improved multi-language features, including automatic subtitling and translation, sounds promising. Considering the importance of user feedback and potential benefits in loud environments, I’d be interested in exploring this further. Regarding speech-to-text tools, nerd-dictation is a good start, and I’m open to collaborating with @baybars and others to delve deeper into this domain.