|
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, 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 |
|
|
|
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("Transcription model", options=asr_model_options, key="sbox") |
|
|
|
st.markdown("## Interview analyzer") |
|
|
|
st.markdown( |
|
""" |
|
**π Enter a YouTube 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']) |
|
|