vosk-api

DeepSpeeech is very old software. Vosk works just fine https://github.com/alphacep/vosk-api. People even run tiny Whisper on Pi, though they have to wait ages.

You need a Raspberry Pi with respeaker microphone. Many assistants to install around - for example https://github.com/iamsrp/dexter and many more. Whisper is a bit slow on RPI and not working well for short phrases. It is more focused on long transcription like podcasts. You can try Vosk instead https://github.com/alphacep/vosk-api

https://github.com/alphacep/vosk-api Your app is neat in that it can record from the Lock Screen. I was curious to try out the new open ai model. Too often, iOS has a problem of too many clicks to do the most basic of things.

Try https://github.com/alphacep/vosk-api/blob/master/csharp/demo...

I wonder if you could train some machine learning model using the data from SponsorBlock and achieve good results on podcasts as well. That way you wouldn't be dependent on a crowdsourced online database for your offline listening. Alternatively, even creating a transscript using something like [1] and scanning for words like "sponsor", "ad" or specific company names might already be a good enough heuristic. [1] https://github.com/alphacep/vosk-api

They might be interested in integrating Vosk, it's a speech-to-text engine that is just a shared library (.so file on Linux) and comes with API support for a variety of languages: https://alphacephei.com/vosk/ https://github.com/alphacep/vosk-api Still, I've found that the Big players have much better recognition models, and the post-processing that I assume they do (grammatical, maybe syntactical inferences that improve the end result) are probably much more powerful too.

Nerd dictation is a purely on-device speech to text program that works pretty well if your computer is fast enough. https://github.com/ideasman42/nerd-dictation get speech models here: https://github.com/alphacep/vosk-api HN discussion: https://news.ycombinator.com/item?id=29972579

In case it's of interest, when I last explored this topic in terms of the Free/Open Source ecosystem I was very impressed with how well VOSK-API performed: https://github.com/alphacep/vosk-api Here's another project that builds on top of VOSK to provide a tighter integration with Linux: https://github.com/ideasman42/nerd-dictation

Did you try Vosk https://github.com/alphacep/vosk-api or Wenet https://github.com/wenet-e2e/wenet

Vosk https://github.com/alphacep/vosk-api

For offline transcription try Vosk https://github.com/alphacep/vosk-api

The package that this project is built on (vosk-api) mentions & includes some examples to demonstrate exactly that type of use case with ffmpeg: "...continuous large vocabulary transcription, zero-latency response with streaming API, reconfigurable vocabulary and speaker identification ... can also create subtitles for movies, transcription for lectures and interviews." * https://github.com/alphacep/vosk-api/blob/master/python/exam... * https://github.com/alphacep/vosk-api/blob/master/python/exam... * https://github.com/alphacep/vosk-api/blob/master/python/exam... (Edit: Also, thanks for introducing me to "libretranslate", looks like an interesting project.)

Yeah, I was really impressed with the project when I encountered it last year when trying out a bunch of FLOSS Speech-To-Text options. It was significantly better than the other FLOSS options I looked at--both in terms of getting it going initially & the quality of the speech to text results. I tested it with a lightly modified version of this example script: https://github.com/alphacep/vosk-api/blob/master/python/exam... What I found particularly interesting was when you have the "partial" recognition output shown in real-time you get to see how--at the end of a sentence--it may change a word earlier in the sentence in the final recognition output based on (I guess) the additional context of the full sentence. (I just did a quick test again (with the installs from my testing last year) using an internal laptop microphone & the test scrip

Talon has an EULA that is enough to send me scrambling for the hills: https://talonvoice.com/EULA.txt Meanwhile, the meat of this speech recognizition is Vosk, which is just Apache-2: https://github.com/alphacep/vosk-api/blob/master/COPYING