vosk-api
vosk-api copied to clipboard
alphacep
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Feature request: Add support for [Wyoming Protocol](https://github.com/rhasspy/rhasspy3/blob/master/docs/wyoming.md) by HomeAssistant with 240k+ active installations. The only current STT that supports Wyoming Protocol is "faster-Whisper" which is extremely slow right now, therefore...
I've done all I can to get this API to work but it's so wildly inaccurate even using the newest gigaspeech model. Is there something in my code causing it...
I'm trying to use gradio with Vosk but it seems the model is not predicting speech. I'm using `test_gradio.py` to predict the speech. Here is the app console output. ...
Hello, is it possible to use **vosk-recasepunc-en-0.22** before the writting of a SubRip file? I have a code like in _https://github.com/alphacep/vosk-api/blob/master/python/example/test_srt.py_ but with 1 word per line. If I use...
Hi, is there a way to show progress bar or percentage status when transcribing? Thanks
Hi, I noticed a strange effect when I checked a set of transcriptions created by running through a number of WAV files in different folders. Sometimes I get slightly different...
Hi all, I am working on vosk-api using Kaldi. In that i am running the c programs to validate the output using the vosk-model-en-in-0.5 model. I am running the test_vosk...
Hello, I had seen that you had previously mentioned that for multilingual feature we should train on multiple languages. Do we need to do it from scratch using Kaldi, and...
Hi, I have some domain-specific audio data, can I use this data to fine-tune the vosk model? Thanks for answering!
Based on this issue of NSFW words being included: https://github.com/ideasman42/nerd-dictation/issues/99 it would be useful to know if the VOSK grammar file can be made to exclude words (instead of limiting...
