File size: 957 Bytes
f4da5b0 | 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 | from transformers import pipeline
from typing import Dict, Any
# Initialize the transcription pipeline
# transcriber = pipeline("automatic-speech-recognition", model="distil-whisper/distil-large-v3")
transcriber = pipeline("automatic-speech-recognition", model="distil-whisper/distil-small.en")
async def send_to_voice_AI(audio_data: bytes) -> Dict[str, Any]:
"""
Transcribes audio data using the Hugging Face Whisper model.
Args:
audio_data (bytes): The raw audio data to be transcribed.
Returns:
Dict[str, Any]: A dictionary containing the transcription result or error message.
"""
print("Transcribing audio")
try:
# Transcribe the audio
result = transcriber(audio_data)
return {"text": result["text"]}
except Exception as e:
print(f"Error during transcription: {str(e)}")
return {"text": "Sorry, an error occurred during transcription."} |