Update app.py

app.py

@@ -31,7 +31,15 @@ from PyPDF2 import PdfReader
 from templates import bot_template, css, user_template
 from xml.etree import ElementTree as ET
 
-# Constants
+# Whisper Constants
+file_path = 'text_output.txt'
+WHISPER_API_URL = 'https://tonpixzfvq3791u9.us-east-1.aws.endpoints.huggingface.cloud'
+WHISPER_headers = {
+    "Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
+    "Content-Type": "audio/wav"
+}
+
+# Llama Constants
 API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
 API_KEY = os.getenv('API_KEY')
 headers = {
@@ -507,11 +515,11 @@ def main():
     # Feedback
     # Step: Give User a Way to Upvote or Downvote
     feedback = st.radio("Step 8: Give your feedback", ("👍 Upvote", "👎 Downvote"))
-
     if feedback == "👍 Upvote":
         st.write("You upvoted 👍. Thank you for your feedback!")
     else:
         st.write("You downvoted 👎. Thank you for your feedback!")
+        
 
 load_dotenv()
 st.write(css, unsafe_allow_html=True)
@@ -534,4 +542,67 @@ with st.sidebar:
             create_file(filename, raw, '', should_save)
 
 if __name__ == "__main__":
-    main()
+    main()
+
+
+
+def whisper(filename):
+    with open(filename, "rb") as f:
+        data = f.read
+    #try:
+    response = requests.post(WHISPER_API_URL, headers=WHISPER_headers, data=data)
+    #except:
+    #    st.write('Whisper Voice Speech to Text Model is asleep. Starting up now on T4 - please give 3 minutes then retry as KEDA scales up from zero to activate running container(s).')
+    return response.json()
+
+def whisper_generate_filename(prompt, file_type):
+    central = pytz.timezone('US/Central')
+    safe_date_time = datetime.now(central).strftime("%m%d_%H%M")
+    replaced_prompt = prompt.replace(" ", "_").replace("\n", "_")
+    safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:90]
+    return f"{safe_date_time}_{safe_prompt}.{file_type}"
+
+def whisper_save_and_play_audio(audio_recorder):
+    audio_bytes = audio_recorder()
+    if audio_bytes:
+        filename = whisper_generate_filename("Recording", "wav")
+        with open(filename, 'wb') as f:
+            f.write(audio_bytes)
+        st.audio(audio_bytes, format="audio/wav")
+        return filename
+
+def whisper_transcribe_audio(filename):
+    output = whisper(filename)
+    return output
+
+def whisper_save_transcription(transcription):
+    with open(file_path, 'a') as f:
+        f.write(f"{transcription}\n")
+
+def whisper_load_previous_transcriptions():
+    if os.path.exists(file_path):
+        with open(file_path, 'r') as f:
+            return f.read()
+    return ""
+
+def whisper_main():
+    st.title("Speech to Text 🎤📝")
+    st.write("Record your speech and get the text. 🗨️")
+
+    previous_transcriptions = whisper_load_previous_transcriptions()
+    text_area = st.text_area("Transcriptions:", previous_transcriptions, height=400)
+
+    filename = whisper_save_and_play_audio(audio_recorder)
+    if filename is not None:
+        try:
+            transcription = whisper_transcribe_audio(filename)
+        
+            # Update the text area with new transcription
+            updated_transcriptions = f"{previous_transcriptions}\n{transcription}"
+            st.text_area("Transcriptions:", updated_transcriptions, height=400)
+        
+            # Save the new transcription to file
+            whisper_save_transcription(transcription)
+        except:
+            st.write('Whisperer loading..')
+