nickmuchi commited on
Commit
04d5d81
β€’
1 Parent(s): fc9fa80

Update 01_🏠_Home.py

Browse files
Files changed (1) hide show
  1. 01_🏠_Home.py +5 -5
01_🏠_Home.py CHANGED
@@ -15,6 +15,8 @@ nltk.download('punkt')
15
 
16
  from nltk import sent_tokenize
17
 
 
 
18
  st.sidebar.header("Home")
19
 
20
  asr_model_options = ['tiny.en','base.en','small.en']
@@ -32,10 +34,10 @@ st.markdown(twitter_link)
32
  st.markdown(
33
  """
34
  This app assists finance analysts with transcribing and analysis Earnings Calls by carrying out the following tasks:
35
- - Transcribing earnings calls using Open AI's [Whisper](https://github.com/openai/whisper).
36
  - Analysing the sentiment of transcribed text using the quantized version of [FinBert-Tone](https://huggingface.co/nickmuchi/quantized-optimum-finbert-tone).
37
  - Summarization of the call with [FaceBook-Bart-Large-CNN](https://huggingface.co/facebook/bart-large-cnn) model with entity extraction
38
- - Question Answering engine powered by Langchain and [Sentence Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2).
39
  - Knowledge Graph generation using [Babelscape/rebel-large](https://huggingface.co/Babelscape/rebel-large) model.
40
 
41
  **πŸ‘‡ Enter a YouTube Earnings Call URL below and navigate to the sidebar tabs**
@@ -63,8 +65,6 @@ st.markdown(
63
  unsafe_allow_html=True
64
  )
65
 
66
- upload_wav = st.file_uploader("Upload a .wav sound file ",key="upload")
67
-
68
- auth_token = os.environ.get("auth_token")
69
 
70
  st.markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-earnings-call-whisperer)")
 
15
 
16
  from nltk import sent_tokenize
17
 
18
+ auth_token = os.environ.get("auth_token")
19
+
20
  st.sidebar.header("Home")
21
 
22
  asr_model_options = ['tiny.en','base.en','small.en']
 
34
  st.markdown(
35
  """
36
  This app assists finance analysts with transcribing and analysis Earnings Calls by carrying out the following tasks:
37
+ - Transcribing earnings calls using Open AI's Whisper API, takes approx 3mins to transcribe a 1hr call less than 25mb in size.
38
  - Analysing the sentiment of transcribed text using the quantized version of [FinBert-Tone](https://huggingface.co/nickmuchi/quantized-optimum-finbert-tone).
39
  - Summarization of the call with [FaceBook-Bart-Large-CNN](https://huggingface.co/facebook/bart-large-cnn) model with entity extraction
40
+ - Question Answering Search engine powered by Langchain and [Sentence Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2).
41
  - Knowledge Graph generation using [Babelscape/rebel-large](https://huggingface.co/Babelscape/rebel-large) model.
42
 
43
  **πŸ‘‡ Enter a YouTube Earnings Call URL below and navigate to the sidebar tabs**
 
65
  unsafe_allow_html=True
66
  )
67
 
68
+ upload_wav = st.file_uploader("Upload a .wav/.mp3/.mp4 sound file ",key="upload")
 
 
69
 
70
  st.markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-earnings-call-whisperer)")