ExpiredPopsicle/whisper-live
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Default microphone option and selection for linux users

Browse Source
This commit is contained in:
John Ciubuc 2023-01-14 22:31:04 -06:00
parent f180571916
commit 0625e35b87
1 changed files with 39 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
transcribe_demo.py
View File

@ -11,11 +11,12 @@ from datetime import datetime, timedelta
from queue import Queue
from tempfile import NamedTemporaryFile
from time import sleep
from sys import platform
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--model", default="medium", help="Model to use",
parser.add_argument("--model", default="tiny", help="Model to use",
choices=["tiny", "base", "small", "medium", "large"])
parser.add_argument("--non_english", action='store_true',
help="Don't use the english model.")
@ -26,8 +27,42 @@ def main():
parser.add_argument("--phrase_timeout", default=3,
help="How much empty space between recordings before we "
"consider it a new line in the transcription.", type=float)
if 'linux' in platform:
parser.add_argument("--default_microphone", default='pulse',
help="Default microphone name for SpeechRecognition. "
"Run this with 'list' to view available Microphones.", type=str)
args = parser.parse_args()
# The last time a recording was retreived from the queue.
phrase_time = None
# Current raw audio bytes.
last_sample = bytes()
# Thread safe Queue for passing data from the threaded recording callback.
data_queue = Queue()
# We use SpeechRecognizer to record our audio because it has a nice feauture where it can detect when speech ends.
recorder = sr.Recognizer()
recorder.energy_threshold = args.energy_threshold
# Definitely do this, dynamic energy compensation lowers the energy threshold dramtically to a point where the SpeechRecognizer never stops recording.
recorder.dynamic_energy_threshold = False
# Important for linux users.
# Prevents permanent application hang and crash by using the wrong Microphone
if 'linux' in platform:
mic_name = args.default_microphone
if not mic_name or mic_name == 'list':
print("Available microphone devices are: ")
for index, name in enumerate(sr.Microphone.list_microphone_names()):
print(f"Microphone with name \"{name}\" found")
return
else:
for index, name in enumerate(sr.Microphone.list_microphone_names()):
if mic_name in name:
source = sr.Microphone(sample_rate=16000, device_index=index)
break
else:
source = sr.Microphone(sample_rate=16000)
# Load / Download model
model = args.model
if args.model != "large" and not args.non_english:
model = model + ".en"
@ -39,20 +74,6 @@ def main():
temp_file = NamedTemporaryFile().name
transcription = ['']
# The last time a recording was retreived from the queue.
phrase_time = None
# Current raw audio bytes.
last_sample = bytes()
# Thread safe Queue for passing data from the threaded recording callback.
data_queue = Queue()
# We use SpeechRecognizer to record our audio because it has a nice feauture where it can detect when speech ends.
recorder = sr.Recognizer()
recorder.energy_threshold = args.energy_threshold
# Definitely do this, dynamic energy compensation lowers the energy threshold dramtically to a point where the SpeechRecognizer never stops recording.
recorder.dynamic_energy_threshold = False
source = sr.Microphone(sample_rate=16000)
with source:
recorder.adjust_for_ambient_noise(source)