File size: 1,106 Bytes
d0584cc 2ed87be d0584cc 2ed87be d0584cc 2ed87be d0584cc 2ed87be d0584cc 2ed87be |
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 |
from transformers import pipeline
import librosa # Or soundfile
import os
# Initialize the ASR pipeline with a specific model
# Using a smaller Whisper model for quicker setup, but larger models offer better accuracy
asr_pipeline = pipeline(
"automatic-speech-recognition",
model="openai/whisper-tiny.en",
)
def transcribe_audio(audio_filepath):
"""
Transcribes an audio file using the Hugging Face ASR pipeline.
"""
try:
transcription = asr_pipeline(audio_filepath, return_timestamps=True)
return transcription["text"]
except Exception as e:
return f"Error during transcription: {e}"
# Example usage:
if __name__ == "__main__":
audio_file = "./downloaded_files/1f975693-876d-457b-a649-393859e79bf3.mp3"
if os.path.exists(audio_file): # Check if the (placeholder or real) file exists
print(f"Attempting to transcribe: {audio_file}")
transcribed_text = transcribe_audio(audio_file)
print(f"Transcription:\n{transcribed_text}")
else:
print(f"File not found: {audio_file}. Please provide a valid audio file.") |