Update functions.py

functions.py

@@ -2,11 +2,9 @@ import tiktoken
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_chroma import Chroma
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings
-from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from transformers import pipeline
 from app_config import VECTOR_MAX_TOKENS, VECTORS_TOKEN_OVERLAP_SIZE
 from langchain.docstore.document import Document
-import torch
 from pytube import YouTube
 from dotenv import load_dotenv
 from pathlib import Path
@@ -44,25 +42,9 @@ def save_audio_file(url):
         print("Connection Error")
 
 def get_audio_transcription():
-    # whisper  = pipeline("automatic-speech-recognition",
-    #                 "openai/whisper-tiny.en")
-    device = "cuda:0" if torch.cuda.is_available() else "cpu"
-    torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-    model_id = "distil-whisper/distil-large-v2"
-    model = AutoModelForSpeechSeq2Seq.from_pretrained(
-        model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
-    )
-    model.to(device)
-    processor = AutoProcessor.from_pretrained(model_id)
-    whisper = pipeline(
-        "automatic-speech-recognition",
-        model=model,
-        tokenizer=processor.tokenizer,
-        feature_extractor=processor.feature_extractor,
-        max_new_tokens=128,
-        torch_dtype=torch_dtype,
-        device=device,
-    )
+    whisper  = pipeline("automatic-speech-recognition",
+                    "openai/whisper-large-v3")
+   
     transcription = whisper("yt_audio.mp4",
                     chunk_length_s=30,
                     stride_length_s=5,