This is absolute garbage python as I am neither a python developer, nor a good developer. I was trying to play around with real time transcriptions. However, it does work!
> * recording
* done recording
Recording saved to file.wav
Press enter to transcribe
/Users/laptop/Development/Personal/Public/pythonProject1/venv/lib/python3.9/site-packages/whisper/transcribe.py:70: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")
Detected language: english
Goodbye, I need to go pick up my wife.
Press enter to start recording
Any improvements welcome here.
```
# This is a sample Python script.
# Press ⌃R to execute it or replace it with your code.
# Press Double ⇧ to search everywhere for classes, files, tool windows, actions, and settings.
def print_hi(name):
# Use a breakpoint in the code line below to debug your script.
print(f'Hi, {name}') # Press ⌘F8 to toggle the breakpoint.
def record_microphone(seconds):
import pyaudio
import wave
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
RECORD_SECONDS = seconds
WAVE_OUTPUT_FILENAME = "file.wav"
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
frames_per_buffer=CHUNK)
print("* recording")
frames = []
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
frames.append(data)
print("* done recording")
stream.stop_stream()
stream.close()
p.terminate()
wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()
return WAVE_OUTPUT_FILENAME
if __name__ == '__main__':
seconds = 5
while True:
print("Press enter to start recording")
input()
filename = record_microphone(seconds)
print("Recording saved to " + filename)
print("Press enter to transcribe")
input()
import whisper
model = whisper.load_model("base")
result = model.transcribe(filename)
print(result["text"])
```