second commit

utils/audit/audit_audio.py

@@ -4,7 +4,16 @@ import scipy.io.wavfile as wavfile
 from pydub import AudioSegment
 import io
 import tiktoken
-from transcript_audio import transcript_audio
+from openai import OpenAI
+
+def transcript_audio_func(audio_file):
+    client = OpenAI()
+    transcription = client.audio.transcriptions.create(
+        model="whisper",
+        file=audio_file
+    )
+
+    return transcription.text
 
 def count_tokens(input_string: str) -> int:
     tokenizer = tiktoken.get_encoding("cl100k_base")
@@ -35,7 +44,7 @@ def evaluate_audio_quality(file) -> dict:
     snr = calculate_snr(audio_data)
 
     #get the transcription of the audio
-    transcription = transcript_audio(file)
+    transcription = transcript_audio_func(file)
     
     return {"volume": volume, "SNR": snr,"transcription": transcription,"number_of_tokens": count_tokens(transcription),"duration": duration}
 

utils/audit/transcript_audio.py

@@ -1,11 +1,13 @@
 from openai import OpenAI
-client = OpenAI()
 
 
-def transcript_audio(audio_file):
+
+
+def transcript_audio_func(audio_file):
+    client = OpenAI()
     transcription = client.audio.transcriptions.create(
         model="whisper",
         file=audio_file
     )
-    
+
     return transcription.text