File size: 2,615 Bytes
31defb6 faa1ca7 31defb6 04d5d81 31defb6 979d3c4 964d470 5b6b68a 9c357bf adbb180 31defb6 bc67d8d cc0a2f2 31defb6 04d5d81 31defb6 4896ebd 04d5d81 31defb6 a2934a4 08a4021 a11f33b 3bf7ebf 6a7b968 31defb6 6a50b6a 7e709b3 6a29b7c 957ac20 31defb6 698009d 31defb6 875ef07 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
import whisper
import os
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
from sentence_transformers import SentenceTransformer, CrossEncoder, util
import streamlit as st
import en_core_web_lg
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']
asr_model_name = st.sidebar.selectbox("Whisper Model Options", options=asr_model_options, key="sbox")
st.markdown("## Earnings Call Analysis Whisperer")
twitter_link = """
[](https://twitter.com/nickmuchi)
"""
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 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 [philschmid/flan-t5-base-samsum](https://huggingface.co/philschmid/flan-t5-base-samsum) model with entity extraction
- Question Answering Search engine powered by Langchain and [Sentence Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2).
**👇 Enter a YouTube Earnings Call URL below and navigate to the sidebar tabs**
"""
)
if 'sbox' not in st.session_state:
st.session_state.sbox = asr_model_name
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, example below is McDonalds Earnings Call Q1 2023",
value="https://www.youtube.com/watch?v=4p6o5kkZYyA")
if 'url' not in st.session_state:
st.session_state['url'] = ""
st.session_state['url'] = url_input
st.markdown(
"<h3 style='text-align: center; color: red;'>OR</h3>",
unsafe_allow_html=True
)
upload_wav = st.file_uploader("Upload a .wav/.mp3/.mp4 audio file ",key="upload",type=['.wav','.mp3','.mp4'])
st.markdown("")
|