01_🏠_Home.py

import whisper
import os
from pytube import YouTube
import pandas as pd
import plotly_express as px
import nltk
import plotly.graph_objects as go
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
from sentence_transformers import SentenceTransformer, CrossEncoder, util
import streamlit as st
import en_core_web_lg

nltk.download('punkt')

from nltk import sent_tokenize


st.set_page_config(
    page_title="Home",
    page_icon="📞",
)

st.sidebar.header("Home")
st.markdown("## Earnings Call Analysis Whisperer")

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).
    - 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
    - Semantic search engine with [Sentence-Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) and reranking results with a Cross-Encoder.
    
    **👇 Enter a YouTube Earnings Call URL below and navigate to the sidebar tabs** 
    
"""
)

if "url" not in st.session_state:
    st.session_state.url = ''
    
if "earnings_passages" not in st.session_state:
    st.session_state["earnings_passages"] = ''
    
if "sen_df" not in st.session_state:
    st.session_state['sen_def'] = ''
        
url_input = st.text_input(
        label='Enter YouTube URL, e.g "https://www.youtube.com/watch?v=8pmbScvyfeY"', key="url")
        
st.markdown(
    "<h3 style='text-align: center; color: red;'>OR</h3>",
    unsafe_allow_html=True
)

upload_wav = st.file_uploader("Upload a .wav sound file ",key="upload")

auth_token = os.environ.get("auth_token")

st.markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-earnings-call-whisperer)")

from functions import *