RealtimeSTT
RealtimeSTT copied to clipboard
KoljaB
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Currently if real time transcription continues for a long time then sentence appear to be a huge so it's processing takes a lot of time even with using Cuda. Is...
I was wondering how you solve the following issue. RealTimeSTT: root - ERROR - Error initializing porcupine wake word detection engine: dlopen(/Users/garlandwong/Documents/PycharmProjects/RealtimeSTT/venv/lib/python3.12/site-packages/pvporcupine/lib/mac/x86_64/libpv_porcupine.dylib, 0x0006): tried: '/Users/garlandwong/Documents/PycharmProjects/RealtimeSTT/venv/lib/python3.12/site-packages/pvporcupine/lib/mac/x86_64/libpv_porcupine.dylib' (mach-o file, but is an...
Spent whole day to try this run by different ways and with no one had success. Always some errors. Here is the docker error python3: can't open file '/app/example_browserclient/server.py': [Errno...
I develope the mic reconnection code. Problem : When I tested it by disconnecting and turning on the microphone connected via Bluetooth like capture, an error occurred and the voice...
https://github.com/user-attachments/assets/3f2f5a93-ba1a-4043-b670-3fb6593b8f66 When I tested it by disconnecting and turning on the microphone connected via Bluetooth like capture, an error occurred and the voice recognition program stopped. **So I am attaching...
I have added the translate task like so in the _transcription_worker. ``` segments, info = model.transcribe( audio, language=language if language else None, beam_size=beam_size, initial_prompt=initial_prompt, suppress_tokens=suppress_tokens, task="translate" ) ``` Is there...
I guess it may be because my processing speed is slow and the transcription takes a long time. After vad detects silence, it calls stop() and then does not send...
#clint.js gives deprecation error due to inputBuffer and createScriptProcessor. ``` // Request access to the microphone navigator.mediaDevices.getUserMedia({ audio: true }) .then(stream => { let audioContext = new AudioContext(); let source...
I believe an effective way to improve overall stability is to use the previously generated transcription results as the next prompt.
https://github.com/KoljaB/RealtimeSTT/blob/d02be1f6a6757f518864deb3f35a53b6b3563f21/RealtimeSTT/audio_recorder.py#L1209 I'm trying to track down why on my system sometimes (usually) when I Ctrl-C to shut down my app shutdown will hang on the aforementioned line. I tried subclassing...
