main app module developed

API/main.py

+import numpy as np
+import tempfile
+import soundfile as sf
+import shutil
+import os
+import cv2
+import tempfile
+import shutil
+import uvicorn
+
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import FileResponse , JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+
+from service01.self_improvement import function01_main
+from service01.text_to_time_and_number import word_to_time,word_to_number,extract_time_from_text,extract_numbers_from_text
+from service02.Handwriting_recognition import Handwriting_recognition
+from service03.lj_functiono3 import speech_to_text , scoring , text_to_speech,scoring_letter
+
+
+
+app = FastAPI(title="Learn_Joy",
+    description="FastAPI for Learn_Joy",
+    version="0.104.1")
+
+# Allow all origins (replace * with specific origins if needed)
+app.add_middleware(
+  CORSMiddleware,
+  allow_origins=["*"],
+  allow_credentials=True,
+  allow_methods=["*"],
+  allow_headers=["*"],
+)  
+
+
+@app.get("/")
+def read_root():
+    return {"Hello": "World"}
+  
+  
+#####FUNCTION01############################
+  
+  
+@app.post("/function01/self_improvement/")
+async def function1_self_improvement(player_name:str):
+
+    out_put=function01_main(player_name=player_name)
+    
+    return out_put
+  
+  
+
+@app.post("/function01/STnumber/")    
+async def ST_number(audio_file: UploadFile = File(...)):
+
+  # Create a temporary directory
+  temp_dir = tempfile.mkdtemp()
+  # Create a temporary file path
+  temp_file_path = os.path.join(temp_dir, audio_file.filename)
+  # Write the uploaded file content to the temporary file
+  with open(temp_file_path, "wb") as temp_file:
+      shutil.copyfileobj(audio_file.file, temp_file)
+
+
+  #auto speech recognition
+  transcriptions=speech_to_text(temp_file_path)
+  #print(transcriptions)
+
+  # Clean up: Remove the temporary directory and its contents
+  shutil.rmtree(temp_dir)
+
+  #convert text to number
+  try:
+    number_sent=word_to_number(transcriptions)
+    number=extract_numbers_from_text( number_sent)
+
+    return {"ID":1,"Number":number}
+  
+  except Exception as e:
+    return{"ID": 0,"Number":"Rate limit reached for gpt-3.5-turbo in organization org-ZZwojjJF2JZq3FiZnZ2tOhmn on requests per min (RPM): Limit 3, Used 3"}
+
+
+
+@app.post("/function01/STtime/")    
+async def ST_time(audio_file: UploadFile = File(...)):
+
+  # Create a temporary directory
+  temp_dir = tempfile.mkdtemp()
+  # Create a temporary file path
+  temp_file_path = os.path.join(temp_dir, audio_file.filename)
+  # Write the uploaded file content to the temporary file
+  with open(temp_file_path, "wb") as temp_file:
+      shutil.copyfileobj(audio_file.file, temp_file)
+
+
+  #auto speech recognition
+  transcriptions=speech_to_text(temp_file_path)
+  #print(transcriptions)
+  # Clean up: Remove the temporary directory and its contents
+  shutil.rmtree(temp_dir)
+
+  #convert text to time
+  try:
+    time_sent=word_to_time(transcriptions)
+    time=extract_time_from_text(time_sent)
+
+    return {"ID":1,"Time":time}
+  except Exception as e:
+    return{"ID": 0,"Time":"Rate limit reached for gpt-3.5-turbo in organization org-ZZwojjJF2JZq3FiZnZ2tOhmn on requests per min (RPM): Limit 3, Used 3"}
+
+
+
+#############Function02#########################
+
+#blackboard white letter
+@app.post("/function02/recognition_BB/")
+async def function2_recognition(BB_image:UploadFile =File(...)):
+    out_put={}
+    temp_dir = tempfile.mkdtemp()
+
+    # Create a temporary file path foe doner file
+    BB_image_path = os.path.join(temp_dir,BB_image.filename)
+
+    # Write the uploaded file content to the temporary file
+    with open(BB_image_path, "wb") as temp_file1:
+      shutil.copyfileobj(BB_image.file, temp_file1)
+
+    out_put= Handwriting_recognition(BB_image=BB_image_path,WB_image=None)
+
+
+    # Clean up: Remove the temporary directory and its contents
+    shutil.rmtree(temp_dir)
+
+    return out_put
+
+#whiteboard blackletter
+@app.post("/function02/recognition_WB/")
+async def function2_recognition(WB_image:UploadFile =File(...)):
+    out_put={}
+    # Create a temporary directory
+    temp_dir = tempfile.mkdtemp()
+    WB_image_path = os.path.join(temp_dir,WB_image.filename)
+
+    # Write the uploaded file content to the temporary file
+    with open(WB_image_path, "wb") as temp_file2:
+        shutil.copyfileobj(WB_image.file, temp_file2)
+
+
+    out_put= Handwriting_recognition(BB_image=None,WB_image=WB_image_path)
+
+    # Clean up: Remove the temporary directory and its contents
+    shutil.rmtree(temp_dir)
+
+
+    return out_put
+
+##############FUNCTION3#####################
+
+@app.post("/function3/STT_words/")    
+async def main_fun03_words(words:str, audio_file: UploadFile = File(...)):
+  
+  # Create a temporary directory
+  temp_dir = tempfile.mkdtemp()
+  
+  # Create a temporary file path
+  temp_file_path = os.path.join(temp_dir, audio_file.filename)
+
+  # Write the uploaded file content to the temporary file
+  with open(temp_file_path, "wb") as temp_file:
+      shutil.copyfileobj(audio_file.file, temp_file)
+
+
+  #auto speech recognition
+  transcriptions=speech_to_text(temp_file_path)
+
+  #get the prediction score
+  final_sent_score,final_word_score,missing_voice2=scoring(words,transcriptions)
+  
+  
+  #return score 
+  voice_score=''
+  voice_sent=''
+
+
+  if int(final_sent_score) >= int(final_word_score):
+    voice_score=np.round(final_sent_score)
+
+  else :
+    voice_score=np.round(final_word_score)
+
+
+  if int(voice_score)==100:
+    voice_sent=f"WOW !!!! YOU WIN !!!, You got hundred percent score"
+
+  else:
+    voice_sent=f"You got less than hundred percent score, Please try these words {missing_voice2}"
+
+  #text to speech
+  speech_array=text_to_speech(voice_sent)
+  
+  # Create a temporary file to store the audio data
+  with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp2_file:
+      temp_filename = temp2_file.name
+      sf.write(temp_filename,speech_array, samplerate=16000, format='WAV')
+
+ 
+
+  # Clean up: Remove the temporary directory and its contents
+  shutil.rmtree(temp_dir)
+  
+  json_data={"final_sent_score":np.round(final_sent_score), "final_word_score":np.round(final_word_score), "missing_voice2":missing_voice2}
+  # Return the audio file as a response & jasonrespons
+ 
+  #return [{"final_sent_score":np.round(final_sent_score), "final_word_score":np.round(final_word_score), "missing_voice2":missing_voice2},FileResponse(temp_filename, media_type="audio/wav", filename="speech.wav")]
+  return {"Scoring":json_data,"audio_file":FileResponse(temp_filename, media_type="audio/wav", filename="speech.wav")}
+
+  #return [JSONResponse(content=json_data, status_code=200, media_type="application/json", headers={"Scoring": "final_sent_score,final_word_score,missing_voice2"}),
+    #        FileResponse(temp_filename, media_type="audio/wav", filename="speech.wav")]
+    
+  
+@app.post("/function3/STT_letter/")    
+async def main_fun03_letter(letter:str, audio_file: UploadFile = File(...)):
+  
+  # Create a temporary directory
+  temp_dir = tempfile.mkdtemp()
+  
+  # Create a temporary file path
+  temp_file_path = os.path.join(temp_dir, audio_file.filename) 
+
+  # Write the uploaded file content to the temporary file
+  with open(temp_file_path, "wb") as temp_file:
+      shutil.copyfileobj(audio_file.file, temp_file)
+
+
+  #auto speech recognition
+  transcriptions=speech_to_text(temp_file_path)
+  #print(transcriptions)
+
+  #get the prediction score
+  score=scoring_letter(letter,transcriptions)
+  
+  
+  #return score 
+  missing_letter=[]
+  voice_sent=''
+
+
+  if int(score) == 100:
+     pass
+    
+  else :
+    missing_letter.append(letter)
+
+
+  if int(score)==100:
+    voice_sent=f"WOW !!!! YOU WIN !!!, You got hundred percent score"
+
+  else:
+    voice_sent=f"You got less than hundred percent score, Please try letter {missing_letter}"
+
+  #text to speech
+  speech_array=text_to_speech(voice_sent)
+  
+  # Create a temporary file to store the audio data
+  with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp2_file:
+      temp_filename = temp2_file.name
+      sf.write(temp_filename,speech_array, samplerate=16000, format='WAV')
+
+ 
+
+  # Clean up: Remove the temporary directory and its contents
+  shutil.rmtree(temp_dir)
+  
+  json_data={"final_sent_score":int(score), "missing_Letter":missing_letter}
+  # Return the audio file as a response & jasonrespons
+ 
+  #return [{"final_sent_score":np.round(final_sent_score), "final_word_score":np.round(final_word_score), "missing_voice2":missing_voice2},FileResponse(temp_filename, media_type="audio/wav", filename="speech.wav")]
+  return {"Scoring":json_data,"audio_file":FileResponse(temp_filename, media_type="audio/wav", filename="speech.wav")}
+
+  #return [JSONResponse(content=json_data, status_code=200, media_type="application/json", headers={"Scoring": "final_sent_score,final_word_score,missing_voice2"}),
+    #        FileResponse(temp_filename, media_type="audio/wav", filename="speech.wav")]
+    
+  
+
+
+
+  
+#uvicorn main:app --reload
+