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
Error with run node.js lib on pi4: vosk/lib/linux-x86_64/libvosk.so: wrong ELF class: ELFCLASS64 Are there any solutions?
1. Which is the sample codes to run multi-threading in python?
Hi, I could make a script that works as a py file, but when I try to run pyinstaller to get an exe of the file I get that error,...
When i test with microphone. I get the following error: ASSERTION_FAILED (VoskAPI:CompactLatticeStateTimes():lattice-functions.cc:113) Assertion failed: (lat.Start() == 0) Aborted (core dumped) Here is my model file structure: model/ ├── final.mdl ├──...
Hello: I want to use C# to save all the voice recognized text in a file, so I can edit it later. I found to use Console.WriteLine to show the...
可以实现语音评测吗? Can voice evaluation be implemented? 输入一段文字和一段声音，评测文字与声音的重合度。 Enter a text and a sound to evaluate the coincidence of text and sound.
I'm looking for an alternative to verify users by their voice. Do you provide sample code for that? Thanks and congratulations on your project
Hi, I have latest vosk running on ubuntu 20.04, latest kaldi. I downloaded the vosk-model-en-us-0.22-compile, and just added one simple new word to existing extra.txt. I run compile-graph.sh but getting...
App fails to unpack the model with the following error: ``` java.lang.Error: Failed to unpack the model: model-en-us/uuid ``` None of the first three english models includes uuid subfolder. This...
