IbrahimF96

Potentially, it’s about the audio quality more than anything. If there are not multiple voices talking over each other or music playing over it then it has a good chance

Yes! It supports many languages, you’ve made me realise a gap in the messaging in terms of communicating that value.

It can support up to 99 but the subtitle generation quality tends to decreases with more obscure languages as they wouldn’t have been in the training data

It's not fully solved, there are still errors but its improved a lot the past few years especially compared to Youtube. The best approximation is the Whisper models atm as far as I have seen. There is a write up here on hugging face which talks more about the models and the benchmarks against it.

https://huggingface.co/openai/whisper-large-v3

Yeah I can relate haha, that is one of the things I questioned, if a desktop app was the best format for this app. I do feel the majority of people are drifting more towards mobile tbh so may have to make a companion app lol

Technically its still free since there is no card requirement but we can agree to disagree here

Thanks, I appreciate it!

True, I would say though from my personal experience there is a serious study element inherent to learning languages to a high level too. So it depends on what the user wants, there are gamified apps like Duolingo but the efficacy of it has been questioned over the years

By study I mean adding to Anki for example as a flashcard

Ahh nice, hope it goes well!

Yeah that is a very good point, it’s something I thought about a lot when positioning the app. Essentially there are 2 mitigations to this, one is that it’s not really ideal for beginners and mainly targeting intermediate learners who can recognise or at least question errors to a certain extent but don’t want to create the entire subtitle file themselves. There is an inline editor for them to fix the errors.

The other thing is the speech recognition models are very sensitive to the audio. If the audio quality is good then the model would do a good job, I’m not sure how much experience you have with Whisper Large but it is very capable on normal speech. The issues arise when there are many competing sounds overriding each other

That’s fair enough! I am curious tho, are there any issues you face while using the app that could be handled better? Or any features that would make it easier to use?

ASR in LR is down often from my experience.

Yeah that is a fair point, it can be replicated but not many people want to replicate an app and would rather pay for it. The functionality is not hard to replicate but the UX side of things and general support and improvements over time is what people have paid for. There is a lifetime option also - yearly was about offering choices.

Nice! Yeah I think the functionality is never very complicated, I'm more so interested the UX and trying to add features that reduce friction and slowly build an app that can be stable and relied upon.

I've only heard of asbplayer and Anki miner before, the others I haven't. It's a great space tbh, people are building all the time. For me specifically it's about trying to serve all languages to the best of my ability, alot of the ones I've come across only focus on Japanese or a small selection of languages. Also I think there's scope to improve UX and reducing friction for non tech savvy people

Yeah I agree the Youtube ones are not very good, I am not sure what they have implemented behind the scenes for it. However this uses the Whisper Large model which is quite a bit better than the Youtube auto generated ones. Only catch is you need to have the video on disk and wait a bit longer lol

Thanks! There is a whole like subsection of language learning called immersion based learning. Fictional sources can be OK just depends on how specialised and unique the vocabulary is.

Yeah that is my suspicion too, I am considering adding an option to transcribe system audio too so it could hook into whatever video or audio is playing on the computer. That would be quite a big change so would like feedback first! hahah

Hi, I am making an app for language learning which generates subtitles to help with this exact problem. Its called SubSmith and free to try, would love some feedback on it!

Working on SubSmith, a language learning tool to help with immersion through auto transcription, popup dictionary and Anki integration.

https://subsmith.app/