vosk-api icon indicating copy to clipboard operation
vosk-api copied to clipboard

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Results 266 vosk-api issues
Sort by recently updated
recently updated
newest added

I'm using the vosk integration in SubtitleEdit (current 3.6.7). Basically, it works very well. But I've found one issue. I noticed when doing audio to text using Japanese big model...

I was trying to use the vosk-model-pt-fb-v0.1.1-pruned model, but it didn't work for me, and it returns the error: ``` ERROR (VoskAPI:Model():model.cc:122) Folder 'C:\Users\Rafael\Meus arquivos\Programação\vosk-model-pt-fb-v0.1.1-pruned' does not contain model files....

follow this codes at[ `https://github.com/alphacep/vosk-api/commit/ad5bec114da79911b3625a281b5abd5902efca9f`](https://github.com/alphacep/vosk-api/issues/702#issuecomment-974921038) but still met follows error: `ASSERTION_FAILED (VoskAPI:CompactLatticeStateTimes():lattice-functions.cc:114) Assertion failed: (lat.Start() == 0)`

Hi I am trying to use vosk library for audio to text convertion in server. When I try to launch multiple apps and use 10-15 clients to run a audio...

Is it possible (now or as the future release option) to convert vosk models to an onnx format to reduce the model size?

I am getting the following issue while running make in vosk-api/src, Kindly help in this issue. thanks in advance ``` g++ -g -O3 -std=c++17 -Wno-deprecated-declarations -fPIC -DFST_NO_DYNAMIC_LINKING -I. -I/media/op_zone/ASR_multi/kaldi_vosk/src -I/media/op_zone/ASR_multi/kaldi_vosk/tools/openfst/include...

I am new to javascript. I want to see how the vosk-browser script worked using the sample script. I downloaded a vosk model, zipped it as tar.gz and put it...

**Edit: just saw there was a new release with "Fixes for lattice construction". Will try that and report back.** Hello there! I'm running parallel transcription jobs using one recognizer instance...

I ran the same file through transcription twice in a row and the output is not identical. The timestamps are very close and the text is too but there are...

https://docs.python.org/3/library/typing.html