RealtimeSTT
RealtimeSTT copied to clipboard
pyaudio Invalid number of channels
I ran the following snippet to initialize the recorder:
from RealtimeSTT import AudioToTextRecorder
recorder_config = {
'spinner': False,
'model': 'large-v2',
'language': 'en',
'silero_sensitivity': 0.4,
'webrtc_sensitivity': 2,
'post_speech_silence_duration': 0.4,
'min_length_of_recording': 0,
'min_gap_between_recordings': 0,
'enable_realtime_transcription': True,
'realtime_processing_pause': 0.2,
'realtime_model_type': 'tiny.en',
'compute_type': 'int8',
}
recorder = AudioToTextRecorder(**recorder_config)
However I receive the error
ERROR:root:Error initializing pyaudio audio recording: [Errno -9998] Invalid number of channels OSError: [Errno -9998] Invalid number of channels
This seems to originate from the audio_interface.open
call within audio_recorder.py
. Running python 3.11 in a virtual environment on mac m3.