update

Dockerfile

@@ -4,6 +4,7 @@
 FROM python:3.9
 
 RUN useradd -m -u 1000 user
+RUN apt-get update && apt-get install -y ffmpeg
 USER user
 ENV PATH="/home/user/.local/bin:$PATH"
 

main.py

@@ -2,7 +2,6 @@ from fastapi import FastAPI, File, UploadFile, HTTPException
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 import torch
 import uvicorn
-import librosa
 import soundfile as sf
 from fastapi.middleware.cors import CORSMiddleware
 import os
@@ -52,15 +51,15 @@ async def transcribe_audio(file: UploadFile = File(...)):
             temp_file.write(await file.read())
             temp_path = temp_file.name
 
-        # Load the audio file using librosa
-        audio, sr = librosa.load(temp_path, sr=16000)
+        # Load the audio file using soundfile
+        audio, sr = sf.read(temp_path)
 
-        # Convert to a format that the model can process (in case the file needs reformatting)
-        processed_path = temp_path  # Reuse temp file if format is already correct
-        sf.write(processed_path, audio, 16000)
+        # Ensure the sample rate is 16000 Hz
+        if sr != 16000:
+            raise HTTPException(status_code=400, detail="Sample rate must be 16000 Hz.")
 
         # Pass the processed audio to the pipeline
-        result = pipe(processed_path)
+        result = pipe(temp_path)
 
         # Remove the temp file after processing
         os.remove(temp_path)
@@ -70,7 +69,7 @@ async def transcribe_audio(file: UploadFile = File(...)):
     
     except Exception as e:
         # Clean up temp file in case of error
-        if os.path.exists(temp_path):
+        if 'temp_path' in locals() and os.path.exists(temp_path):
             os.remove(temp_path)
         raise HTTPException(status_code=500, detail=f"Error occurred: {str(e)}")