SchoolProjects/PizzAI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

removed unused and unnecesary functionality

Browse Source
This commit is contained in:
Looki2000 2023-12-04 23:36:07 +01:00
parent 20238a31bf
commit 0a82dac47a
3 changed files with 35 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
frontend/core.py
View File

@ -37,10 +37,11 @@ class Core:
self.payment_method = payment_method
def set_speech_recog_settings(self, speech_recog_timeout, audio_input_device_name, audio_output_device_name, window_size_sec, vad_threshold, min_silence_duration_ms, speech_pad_ms):
#def set_speech_recog_settings(self, speech_recog_timeout, audio_input_device_name, audio_output_device_name, window_size_sec, vad_threshold, min_silence_duration_ms, speech_pad_ms):
def set_speech_recog_settings(self, speech_recog_timeout, window_size_sec, vad_threshold, min_silence_duration_ms, speech_pad_ms):
self.speech_recog_timeout = speech_recog_timeout
self.audio_input_device_name = audio_input_device_name
self.audio_output_device_name = audio_output_device_name
#self.audio_input_device_name = audio_input_device_name
#self.audio_output_device_name = audio_output_device_name
self.window_size_sec = window_size_sec
self.vad_threshold = vad_threshold
self.min_silence_duration_ms = min_silence_duration_ms
@ -48,19 +49,22 @@ class Core:
def set_tts_settings(self, speaker_wav):
self.speaker_wav = speaker_wav
#self.speaker_wav = speaker_wav
print("Setting TTS speaker... ", end="")
self.tts.change_speaker(speaker_wav)
print("Done!")
def assistant_start(self):
print("Starting assistant...")
print("Setting TTS speaker... ", end="")
self.tts.change_speaker(self.speaker_wav)
print("Done!")
#print("Setting TTS speaker... ", end="")
#self.tts.change_speaker(self.speaker_wav)
#print("Done!")
print("Starting VAD recording thread... ", end="")
self.vad_rec.start_vad_recorder(
target_device_name = self.audio_input_device_name,
#target_device_name = self.audio_input_device_name,
window_size_sec = self.window_size_sec,
vad_threshold = self.vad_threshold,
min_silence_duration_ms = self.min_silence_duration_ms,

8
frontend/core_test.ipynb
View File

@ -11,7 +11,7 @@
"core = Core(\n",
" whisper_model_name = \"large-v3\",\n",
" use_chatgpt_placeholder = False\n",
")\n"
")"
]
},
{
@ -29,13 +29,13 @@
"\n",
"core.set_speech_recog_settings(\n",
" speech_recog_timeout = 2.5,\n",
" audio_input_device_name = \"Virtual\",\n",
" audio_output_device_name = \"placeholder\",\n",
" #audio_input_device_name = \"Virtual\",\n",
" #audio_output_device_name = \"placeholder\",\n",
" window_size_sec = 0.1,\n",
" vad_threshold = 0.6,\n",
" min_silence_duration_ms = 150,\n",
" speech_pad_ms = 0\n",
")\n"
")"
]
},
{

35
frontend/vad_recorder.py
View File

@ -101,7 +101,8 @@ class VADRecorder:
def start_vad_recorder(self, target_device_name, window_size_sec = 0.1, vad_threshold = 0.6, min_silence_duration_ms = 150, speech_pad_ms = 0):
#def start_vad_recorder(self, target_device_name, window_size_sec = 0.1, vad_threshold = 0.6, min_silence_duration_ms = 150, speech_pad_ms = 0):
def start_vad_recorder(self, window_size_sec = 0.1, vad_threshold = 0.6, min_silence_duration_ms = 150, speech_pad_ms = 0):
self.window_size = int(window_size_sec * SAMPLERATE)
@ -112,22 +113,24 @@ class VADRecorder:
self.p = pyaudio.PyAudio()
target_device_index = None
for i in range(self.p.get_device_count()):
device_info = self.p.get_device_info_by_index(i)
if device_info['maxInputChannels'] > 0 and target_device_name in device_info['name']:
target_device_index = i
break
#target_device_index = None
#for i in range(self.p.get_device_count()):
# device_info = self.p.get_device_info_by_index(i)
# if device_info['maxInputChannels'] > 0 and target_device_name in device_info['name']:
# target_device_index = i
# break
#
#if target_device_index is None:
# print(f"No target device found with \"{target_device_name}\" in its name.")
# exit()
#
#try:
# self.stream_in = self.p.open(format=pyaudio.paFloat32, channels=1, rate=SAMPLERATE, input=True, frames_per_buffer=self.window_size, input_device_index=target_device_index)
#except OSError:
# print(f"An unexpected error occured when trying to open device stream with \"{target_device_name}\" in its name. That could be caused by the device being disabled or unplugged.")
# exit()
if target_device_index is None:
print(f"No target device found with \"{target_device_name}\" in its name.")
exit()
try:
self.stream_in = self.p.open(format=pyaudio.paFloat32, channels=1, rate=SAMPLERATE, input=True, frames_per_buffer=self.window_size, input_device_index=target_device_index)
except OSError:
print(f"An unexpected error occured when trying to open device stream with \"{target_device_name}\" in its name. That could be caused by the device being disabled or unplugged.")
exit()
self.stream_in = self.p.open(format=pyaudio.paFloat32, channels=1, rate=SAMPLERATE, input=True, frames_per_buffer=self.window_size)
self.speech = False
self.audios_for_whisper = []