Stack Overflow
Stack Overflow

Questions tagged [vosk]

Questions about Vosk Speech Recognition Library

Vosk is a speech recognition toolkit. The best things in Vosk are:

  • Supports 9 languages - English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese. More to come.
  • Works offline, even on lightweight devices - Raspberry Pi, Android, iOS
  • Installs with simple pip3 install vosk
  • Portable per-language models are only 50Mb each, but there are much bigger server models available.
  • Provides streaming API for the best user experience (unlike popular speech-recognition python packages)
  • There are bindings for different programming languages, too - java/csharp/javascript etc.
  • Allows quick reconfiguration of vocabulary for best accuracy.
  • Supports speaker identification beside simple speech recognition.
65 questions
1
vote
1 answer

How to manipulate audio without saving it in Flask with pydub

I'm creating my first Flask API. I send audio file from React Native to Flask. Then I want to process it with vosk module (convert audio to text). Is it possible to manage it without saving the file on server? This is the code that works but saves…
Xenia
  • 87
  • 6
1
vote
1 answer

Why is my flutter app crashing in release mode and working fine in debug mode?

I am currently developing a voice assisted flutter app using vosk and the vosk-flutter-plugin linked below. https://github.com/alphacep/vosk-flutter The app works completely fine in debug mode but crashes upon opening the view that accesses the…
yanekwd
  • 43
  • 1
  • 4
1
vote
0 answers

realtime speech to text with vosk and streamlit

i am trying to build a realtime offline speech recognition system using vosk and streamlit. i completed the vosk normal statement recognition but it doesnt working in live . when i am using threading in python it gives main thread error and also…
Voleti Nagendra kumar
  • 11
  • 1
1
vote
0 answers

How to add words to the dictionary of the English vosk model?

I am using the english vosk model (vosk-model-en-us-0.22, large) in Python to recognize speech from files. I need to add specific words to it dictionary that are not originally there. In the file at: user\…
user522913
  • 11
  • 1
1
vote
0 answers

from vosk import Model, KaldiRecognizer ImportError: No module named vosk

I am working with vosk software using orange pi zero 256mb and python. I try so many idea and always ı see this error. I installed old version of Vosk and download old-new (.whl) file make a virtual environment (env) but doesnt work anyone.…
Mesut
  • 11
  • 3
1
vote
0 answers

how to submit an rtsp stream to pyaudio for further processing

I have a function that connects to my microphone and recognizes speech as a string with a phrase. It looks like this: import json, pyaudio from Analysis import Voice_tag, nlp from vosk import Model, KaldiRecognizer class VoiseRecorder(): …
Serega
  • 171
  • 8
1
vote
0 answers

how can i fix the error with the "ivector" folder from vosk model?

I wanted to run my Vosk voice recognition project but got this error. How can I fix this? ERROR (VoskAPI:DecodableNnetLoopedOnlineBase():decodable-online-looped.cc:50) Ivector feature dimension mismatch: got -1 but network expects 40 In folder…
Кирилл Мазиев
  • 13
  • 2
1
vote
1 answer

Is it possible to get the timing of phonemes with Vosk, instead of full words?

Vosk outputs the timing of words well, but for syllables / phonemes within words, does Vosk have an option or technique to split the output by those instead?
tscizzle
  • 11,191
  • 15
  • 54
  • 88
1
vote
0 answers

Pygame key-presses don't work on 2nd run of cell in Jupyter Lab

When I run the code below after a kernel restart in Jupyter Lab if I hit the space bar, a highlighted 'aaa' will result (as it should). But, if I ever have to re-run the same cell again (without a kernel restart), a space bar hit will just result in…
multilingualtricker
  • 51
  • 4
1
vote
1 answer

Cannot run .c because of segmentation fault using vosk

I'm on ubuntu 18.04 and i'm trying to run a .c file that came with an API called vosk that i just want to run . The issue is that the python script (which comes standard with the API) works without any problems but after compiling with make the .c…
Birto
  • 71
  • 5
1
vote
1 answer

What does "ERROR: fstsymbols: Saving osymbols but there are no output symbols" means and how can i solve it?

I wanted to update the language model of Kaldi model used in Vosk. I was following the Updating the language model in Vosk Adaptation I had this ERROR: fstsymbols: Saving osymbols but there are no output symbols when I try to run fstsymbols…
323 Kobby
  • 93
  • 2
  • 7
1
vote
1 answer

Creating a project specific Vosk dictionary

I am working on an application which uses Vosk for speech recognition. I would like to create a dictionary for the application which contains only the trigger words and spoken numbers needed by the application. Using command line instructions found…
portsample
  • 1,986
  • 4
  • 19
  • 35
1
vote
2 answers

Electron cannot open shared object file from node_modules folder

On electron, the node module vosk needs to access some shared objects located in node_modules/vosk/lib/. The issue I am having right now is that, when I do require('vosk') in my main.js and try to execute my AppImage file, I get: A JavaScript error…
Sharcoux
  • 5,546
  • 7
  • 45
  • 78
1
vote
0 answers

How to send data from RecordRTC to Vosk for Speech-to-text

I am using a Vosk server for speech-to-text conversion. I send the audio/wav blob data obtained using this method recorder.stopRecording(function() { var blob = this.blob; // below one is recommended var blob = this.getBlob(); }); from…
Ikun
  • 197
  • 1
  • 12
1
vote
1 answer

Need to reload vosk model for every transcription?

The vosk model that I'm using is the vosk-model-en-us-aspire-0.2 (1.4GB). Every time needs quite an amount of time to load the vosk model. Is it necessary to recreate the vosk object every time? It takes much time to load the model if we only load…
Ming Zhong Tan
  • 11
  • 4
1
2
3 4 5