Update main.py

main.py

@@ -9,6 +9,8 @@ import warnings
 from starlette.formparsers import MultiPartParser
 import io
 import random
+import tempfile
+import os
 
 
 MultiPartParser.max_file_size = 200 * 1024 * 1024
@@ -20,15 +22,7 @@ app = FastAPI()
 tokenizer = Wav2Vec2Tokenizer.from_pretrained("./models/tokenizer")
 model = Wav2Vec2ForCTC.from_pretrained("./models/model")
 
-from fastapi.middleware.cors import CORSMiddleware
 
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  # Allows all origins
-    allow_credentials=True,
-    allow_methods=["*"],  # Allows all methods
-    allow_headers=["*"],  # Allows all headers
-)
 
 # Function to download English word list
 def download_word_list():
@@ -93,22 +87,26 @@ async def get_rnc():
     return random.randint(0 , 10)
 
 @app.post('/pronunciation_scoring')
-async def unscripted_root(audio_file: UploadFile):
-    print("Pronunciation Scoring")
-    
-    # Read the UploadFile into memory
-    contents = await audio_file.read()
-    
-    print("Contents:" , contents)
-
-    # Create a BytesIO object from the contents
-    audio_bytes = io.BytesIO(contents)
-    
-    print("audio_bytes:" , audio_bytes)
+async def upload_audio(file: UploadFile = File(...)):
+    # Create a temporary file to store the uploaded audio
+    with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.filename)[1]) as temp_file:
+        # Write the uploaded file content to the temporary file
+        content = await file.read()
+        temp_file.write(content)
+        temp_file_path = temp_file.name
+
+    # Load the audio file using librosa with a fixed sample rate of 16000 Hz
+    audio, sr = librosa.load(temp_file_path, sr=16000)
+        
+        # Process the audio data as needed
+        # For this example, we'll just return some basic information
+    duration = librosa.get_duration(y=audio, sr=sr)
+        
+    print("filename:" , file.filename)
+    print("duration:" , duration)
+    print("sample_rate:" , sr)
 
-    # Load the audio file using librosa
-    audio, sr = librosa.load(audio_bytes)
-    
+    os.unlink(temp_file_path)
     # Tokenize audio
     print("Tokenizing audio...")
     input_values = tokenizer(audio, return_tensors="pt").input_values