vosk-api

OP here - I went with Vosk because it's pretty trivial to lock input down to a set vocabulary (in this case numbers) and from my testing works relatively well on most browsers. (webkit, firefox, etc) https://github.com/alphacep/vosk-api

I helped coding oTranscribe+ [0], which does something similar to what you are asking for. Using ElectronJS and the current, at that moment, version of oTranscribe, there is this desktop application. It also exists as web version and PWA [1]. Language models were those from BSC (Barcelona Supercomputing Center) at the time. The transcription is done via WASM, using Vosk [2] as base. I hope it fits. [0] https://github.com/projecte-aina/oTranscribe-plus [1] https://otranscribe.bsc.es/ [2] https://github.com/alphacep/vosk-api

> It's coming! CMUSphinx used to have something like this, and there are some [1] solutions [2] on the horizon. > > [1]: https://github.com/alphacep/vosk-api/issues/55 > > [2]: https://github.com/outlines-dev/outlines?tab=readme-ov-file#... It's interesting as speech recognition has become more popular than ever through services like Alexa, and other iot devices support for OS speech recognition has very little development. Don't get me started with accessibility apis either... Unfortunately most implementations (especially those that are iot focused) don't have very important features for robust speech recognition. 1. Ability to enable and disable a grammar 2. Modify grammars while the engine is loaded 3. Scoped grammars that are context-specific 4. Recognition callbacks 5. Multiple grammars active simultaneously. Unfortunately I don't t

It's coming! CMUSphinx used to have something like this, and there are some [1] solutions [2] on the horizon. [1]: https://github.com/alphacep/vosk-api/issues/55 [2]: https://github.com/outlines-dev/outlines?tab=readme-ov-file#...

As I understand it DeepSpeech is no longer actively maintained by Mozilla: https://github.com/mozilla/DeepSpeech/issues/3693 For Text To Speech, I've found Piper TTS useful (for situations where "quality"=="realistic"/"natual"): https://github.com/rhasspy/piper For Speech to Text (which AIUI DeepSpeech provided), I've had some success with Vosk: https://github.com/alphacep/vosk-api

first, good initiative! thanks for sharing. i think you gotta be more diligent and careful with the problem statement. checking the weather in Sofia, Bulgaria requires cloud, current information. it's not "random speech". ESP SR capability issues don't mean that you cannot process it locally. the comment was on "voice processing" i.e. sending speech to the cloud, not sending a call request to get the weather information. besides, local intent detection, beyond 400 commands, there are great local STT options, working better than most cloud STTs for "random speech" https://github.com/alphacep/vosk-api https://picovoice.ai/platform/cheetah/

I've been using the Azure Cognitive Services speech recognition and text-to-speech for my own locally run 'speech-to-speech' GPT assistant application. I found the Azure speech recognition to be fantastic, almost never making mistakes. The latency is also at a level that only the big cloud providers can reach. A locally run alternative I use is Vosk [0] but this is nowhere near as polished as Azure speech recognition and limits conversation to simple topics. (Running whisper.cpp locally is not an option for me, too heavy and slow on my machine for a proper conversation) The default Azure models available for text-to-speech are great too. There are around 500 models in a wide variety of languages. Using SSML [1] can also really improve the quality of interactions. A subset of these voices have certain capabilities (like responding with emo

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.