openwakeword/examples/detect_from_microphone.py

64 lines
2.1 KiB
Python

# Copyright 2022 David Scripka. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Imports
import pyaudio
import numpy as np
from openwakeword.model import Model
# Get microphone stream
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1280
audio = pyaudio.PyAudio()
mic_stream = audio.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
# Load pre-trained openwakeword models
owwModel = Model()
# Run capture loop, checking for hotwords
if __name__ == "__main__":
# Predict continuously on audio stream
print("\n\n")
print("#"*100)
print("Listening for wakewords...")
print("#"*100)
print("\n"*13)
while True:
# Get audio
audio = np.frombuffer(mic_stream.read(CHUNK), dtype=np.int16)
# Feed to openWakeWord model
prediction = owwModel.predict(audio)
# Generate output string header
n_spaces = 16
output_string_header = """
Model Name | Score | Wakeword Status
--------------------------------------
"""
for mdl in owwModel.prediction_buffer.keys():
# Add scores in formatted table
scores = list(owwModel.prediction_buffer[mdl])
curr_score = format(scores[-1], '.20f').replace("-", "")
output_string_header += f"""{mdl}{" "*(n_spaces - len(mdl))} | {curr_score[0:5]} | {"--"+" "*20 if scores[-1] <= 0.5 else "Wakeword Detected!"}
"""
# Print results table
print("\033[F"*14)
print(output_string_header, " ", end='\r')