File size: 2,524 Bytes
89ef5a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
# if you dont use pipenv uncomment the following:
# from dotenv import load_dotenv
# load_dotenv()
#Step1: Setup Audio recorder (ffmpeg & portaudio)
# ffmpeg, portaudio, pyaudio
import logging
import speech_recognition as sr
from pydub import AudioSegment
from io import BytesIO
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
def record_audio(file_path, timeout=5, phrase_time_limit=10):
"""
Simplified function to record audio from the microphone and save it as an MP3 file.
Args:
file_path (str): Path to save the recorded audio file.
timeout (int): Maximum time to wait for a phrase to start (in seconds).
phrase_time_lfimit (int): Maximum time for the phrase to be recorded (in seconds).
"""
recognizer = sr.Recognizer()
try:
with sr.Microphone() as source:
logging.info("Adjusting for ambient noise...")
recognizer.adjust_for_ambient_noise(source, duration=1)
logging.info("Start speaking now...")
# Record the audio
logging.info(f"Recording for {phrase_time_limit} seconds...")
audio_data = recognizer.record(source, duration=phrase_time_limit)
# audio_data = recognizer.listen(source, )
logging.info("Recording complete.")
# Convert the recorded audio to an MP3 file
wav_data = audio_data.get_wav_data()
audio_segment = AudioSegment.from_wav(BytesIO(wav_data))
audio_segment.export(file_path, format="mp3", bitrate="128k")
logging.info(f"Audio saved to {file_path}")
except Exception as e:
logging.error(f"An error occurred: {e}")
audio_filepath="patient_message.mp3"
#Step2: Setup Speech to text–STT–model for transcription
def transcription(stt_model, audio_filepath, GROQ_API_KEY):
import os
from groq import Groq
from dotenv import load_dotenv
load_dotenv()
GROQ_API_KEY=os.environ.get("GROQ_API_KEY")
stt_model="whisper-large-v3-turbo"
if GROQ_API_KEY is None:
raise ValueError("GROQ_API_KEY is not set! Add it to your environment or .env file.")
client=Groq(api_key=GROQ_API_KEY)
audio_file=open(audio_filepath, "rb")
transcription=client.audio.transcriptions.create(
model=stt_model,
file=audio_file,
language="en"
)
return transcription.text
|