Earnings-Call-Analysis-Whisperer / 01_🏠_Home.py
nickmuchi's picture
Update 01_🏠_Home.py
979d3c4
raw
history blame
2.48 kB
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 transformers import WhisperProcessor, WhisperForConditionalGeneration
from sentence_transformers import SentenceTransformer, CrossEncoder, util
import streamlit as st
import en_core_web_lg
from functions import *
nltk.download('punkt')
from nltk import sent_tokenize
st.set_page_config(
page_title="Home",
page_icon="πŸ“ž",
)
st.sidebar.header("Home")
asr_model_options = ['base','small']
asr_model_name = st.sidebar.selectbox("Whisper Model", options=asr_model_options, key='sbox')
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.
**πŸ‘‡ 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 'sbox' not in st.session_state:
st.session_state.sbox = ''
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_df'] = ''
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)")