Update 01_🏠_Home.py

01_🏠_Home.py

@@ -15,6 +15,8 @@ nltk.download('punkt')
 
 from nltk import sent_tokenize
 
+auth_token = os.environ.get("auth_token")
+
 st.sidebar.header("Home")
 
 asr_model_options = ['tiny.en','base.en','small.en']
@@ -32,10 +34,10 @@ st.markdown(twitter_link)
 st.markdown(
     """
     This app assists finance analysts with transcribing and analysis Earnings Calls by carrying out the following tasks:
-    - Transcribing earnings calls using Open AI's [Whisper](https://github.com/openai/whisper).
+    - Transcribing earnings calls using Open AI's Whisper API, takes approx 3mins to transcribe a 1hr call less than 25mb in size.
     - Analysing the sentiment of transcribed text using the quantized version of [FinBert-Tone](https://huggingface.co/nickmuchi/quantized-optimum-finbert-tone).
     - Summarization of the call with [FaceBook-Bart-Large-CNN](https://huggingface.co/facebook/bart-large-cnn) model with entity extraction
-    - Question Answering engine powered by Langchain and [Sentence Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2).
+    - Question Answering Search engine powered by Langchain and [Sentence Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2).
     - Knowledge Graph generation using [Babelscape/rebel-large](https://huggingface.co/Babelscape/rebel-large) model.
     
     **👇 Enter a YouTube Earnings Call URL below and navigate to the sidebar tabs** 
@@ -63,8 +65,6 @@ st.markdown(
     unsafe_allow_html=True
 )
 
-upload_wav = st.file_uploader("Upload a .wav sound file ",key="upload")
-
-auth_token = os.environ.get("auth_token")
+upload_wav = st.file_uploader("Upload a .wav/.mp3/.mp4 sound file ",key="upload")
 
 st.markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-earnings-call-whisperer)")