ترجمة المحتوى الصوتي باستخدام GPT-4o: دليل خطوة بخطوة

import base64
 
# Read the WAV file and encode it to base64
with open('audio.wav', 'rb') as audio_file:
    audio_bytes = audio_file.read()
    audio_base64 = base64.b64encode(audio_bytes).decode('utf-8')
 
modalities = ["text"]
prompt = "Transcribe the audio to English text, ignoring background noises."
response_json = process_audio_with_gpt_4o(audio_base64, modalities, prompt)
transcript = response_json['choices'][0]['message']['content']
print(transcript)

glossary_of_terms = "GPT, OpenAI, token"
modalities = ["text", "audio"]
prompt = f"Dub the audio in Arabic, keeping certain terms in English: {glossary_of_terms}."
response_json = process_audio_with_gpt_4o(audio_base64, modalities, prompt)
arabic_transcript = response_json['choices'][0]['message']['audio']['transcript']
print(arabic_transcript)

import sacrebleu
from rouge_score import rouge_scorer
 
reference_text = "Your reference English text here"
candidate_text = "The re-translated English text from Arabic audio"
 
# BLEU Score
bleu = sacrebleu.corpus_bleu([candidate_text], [[reference_text]])
print(f"BLEU Score: {bleu.score}")
 
# ROUGE Score
scorer = rouge_scorer.RougeScorer(['rouge1', 'rougeL'], use_stemmer=True)
scores = scorer.score(reference_text, candidate_text)
print(f"ROUGE-1 Score: {scores['rouge1'].fmeasure}")
print(f"ROUGE-L Score: {scores['rougeL'].fmeasure}")