70 lines
1.7 KiB
Plaintext
70 lines
1.7 KiB
Plaintext
|
{
|
||
|
"cells": [
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"from vad_recorder import VADRecorder\n",
|
||
|
"import time\n",
|
||
|
"\n",
|
||
|
"# Instantiate WhisperWrap with the target device name and other parameters\n",
|
||
|
"vad_rec = VADRecorder()"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"print(\"Starting VAD recording thread\")\n",
|
||
|
"\n",
|
||
|
"try:\n",
|
||
|
" vad_rec.start_vad_recorder(target_device_name=\"Virtual\")\n",
|
||
|
"\n",
|
||
|
"\n",
|
||
|
" recordings_count = 0\n",
|
||
|
" now_speech = False\n",
|
||
|
"\n",
|
||
|
" print(\"Done!\")\n",
|
||
|
" while True:\n",
|
||
|
" if vad_rec.speech != now_speech:\n",
|
||
|
" now_speech = vad_rec.speech\n",
|
||
|
" print(f\"Speech: {now_speech}\")\n",
|
||
|
" if len(vad_rec.audios_for_whisper) != recordings_count:\n",
|
||
|
" recordings_count = len(vad_rec.audios_for_whisper)\n",
|
||
|
" print(f\"Recordings count: {recordings_count}\")\n",
|
||
|
"\n",
|
||
|
" time.sleep(0.01)\n",
|
||
|
"\n",
|
||
|
"except (KeyboardInterrupt, SystemExit):\n",
|
||
|
" print(\"Cleaning up...\")\n",
|
||
|
" vad_rec.stop_vad_recorder()\n"
|
||
|
]
|
||
|
}
|
||
|
],
|
||
|
"metadata": {
|
||
|
"kernelspec": {
|
||
|
"display_name": "Python 3",
|
||
|
"language": "python",
|
||
|
"name": "python3"
|
||
|
},
|
||
|
"language_info": {
|
||
|
"codemirror_mode": {
|
||
|
"name": "ipython",
|
||
|
"version": 3
|
||
|
},
|
||
|
"file_extension": ".py",
|
||
|
"mimetype": "text/x-python",
|
||
|
"name": "python",
|
||
|
"nbconvert_exporter": "python",
|
||
|
"pygments_lexer": "ipython3",
|
||
|
"version": "3.11.6"
|
||
|
}
|
||
|
},
|
||
|
"nbformat": 4,
|
||
|
"nbformat_minor": 2
|
||
|
}
|