def init_speech():
global sf
global tf
global TFAutoModel
global AutoProcessor
import soundfile as sf
import tensorflow as tf
from tensorflow_tts.inference import TFAutoModel
from tensorflow_tts.inference import AutoProcessor
global fastspeech2
global mb_melgan
global processor
# initialize fastspeech2 model.
fastspeech2 = TFAutoModel.from_pretrained(
"tensorspeech/tts-fastspeech2-ljspeech-en")
# initialize mb_melgan model
mb_melgan = TFAutoModel.from_pretrained(
"tensorspeech/tts-mb_melgan-ljspeech-en")
# inference
processor = AutoProcessor.from_pretrained(
"tensorspeech/tts-fastspeech2-ljspeech-en")
inference("Hello sir")
debug("Speech", "init")
def audio_to_text(filename):
try:
with sr.AudioFile(filename) as source:
# listen for the data (load audio to memory)
audio_data = r.record(source)
# recognize (convert from speech to text)
text = r.recognize_google(audio_data)
save(text)
do(text)
debug(text, "said")
except sr.UnknownValueError:
pass
def do(said):
said = (said.lower())
debug(time.perf_counter())
if any(ext in said for ext in hotkey_hotword):
shortcut(said)
open_cmd(said)
search(said)
program_functions(said)
talkings(said)
def init_qa_pipeline():
from transformers import pipeline
global question_answering
question_answering = pipeline("question-answering")
debug("QA Pipeline", "init")
def keep_inputing():
while True:
try:
said = input("Write something: ")
action = threading.Thread(target=do, args=[said]).start()
except KeyboardInterrupt:
break
def start():
with open("opening", "w") as opening:
opening.write("false")
print("started listening")
background_listen_2()
def init_items_thread():
threading.Thread(target=init_speech).start()
threading.Thread(target=init_qa_pipeline).start()
print("Imported Everything")
if __name__ == "__main__":
debug(time.perf_counter())
init_items_thread()
start()
time.sleep(1000)