Update app.py

app.py

@@ -3,40 +3,34 @@ import os
 import soundfile as sf
 import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
-# Assuming you have your .env file configured with necessary API keys or configurations
-# load_dotenv()
 
-# Initialize the model outside the main app function to load it only once
 
 
+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)
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    max_new_tokens=128,
+    chunk_length_s=15,
+    batch_size=16,
+    torch_dtype=torch_dtype,
+    device=device,
+)
 
 def transcribe_audio(audio_file):
-    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)
-    
-    pipe = pipeline(
-        "automatic-speech-recognition",
-        model=model,
-        tokenizer=processor.tokenizer,
-        feature_extractor=processor.feature_extractor,
-        max_new_tokens=128,
-        chunk_length_s=15,
-        batch_size=16,
-        torch_dtype=torch_dtype,
-        device=device,
-    )
     # Save the audio file to a temporary file
     with open("temp_audio_file", "wb") as f:
         f.write(audio_file.getbuffer())