Spaces:
Sleeping
Sleeping
File size: 5,175 Bytes
7ad1106 86572ce 7ad1106 fbe12a1 7ad1106 f7aa67f 7ad1106 5ce03b5 7ad1106 5ce03b5 7ad1106 b5ae4c5 7ad1106 b5ae4c5 7ad1106 5ce03b5 7ad1106 5ce03b5 79050de 5ce03b5 79050de 5ce03b5 67f4d3b 5ce03b5 67f4d3b 178a93a 5ce03b5 67f4d3b 6d6d6e1 5ce03b5 7ad1106 5ce03b5 7ad1106 |
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 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 |
import streamlit as st
from audiorecorder import audiorecorder
import torch
from transformers import pipeline
import torch
import torchaudio
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain import HuggingFaceHub, LLMChain, PromptTemplate
from langchain.memory import ConversationBufferWindowMemory
from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationalRetrievalChain
from langchain.document_loaders.csv_loader import CSVLoader
from langchain.vectorstores import FAISS
import tempfile
from streamlit_chat import message
import streamlit as st
from elevenlabs import set_api_key
from elevenlabs import clone, generate, play
from pydub import AudioSegment
import os
import re
import sys
import pandas as pd
import librosa
from helper import parse_transcription,hindi_to_english,translate_english_to_hindi,hindi_tts
def extract_text_from_html(html):
cleanr = re.compile('<.*?>')
cleantext = re.sub(cleanr, '', html)
def conversational_chat(chain,query):
result = chain({"question": query,
"chat_history": st.session_state['history']})
st.session_state['history'].append((query, result["answer"]))
return result["answer"]
def save_uploaded_file_as_mp3(uploaded_file, output_file_path):
audio = AudioSegment.from_file(uploaded_file)
audio.export(output_file_path, format="mp3")
user_api_key = st.sidebar.text_input(
label="#### Your OpenAI API key 👇",
placeholder="Paste your openAI API key, sk-",
type="password")
def ui():
if user_api_key is not None and user_api_key.strip() != "":
os.environ["OPENAI_API_KEY"] =user_api_key
template = """
Behave like a Telecomm customer servce call agent and don't include any website address, compnay name or any other parameter in your output
{history}
Me:{human_input}
Jack:
"""
prompt = PromptTemplate(
input_variables=["history", "human_input"],
template=template
)
llm_chain = LLMChain(
llm = ChatOpenAI(temperature=0.0,model_name='gpt-3.5-turbo'),
prompt=prompt,
verbose=True,
memory=ConversationBufferWindowMemory(k=2)
)
if 'history' not in st.session_state:
st.session_state['history'] = []
if 'generated' not in st.session_state:
st.session_state['generated'] = []
if 'past' not in st.session_state:
st.session_state['past'] = []
if user_api_key is not None and user_api_key.strip() != "":
eleven_labs_api_key = st.sidebar.text_input(
label="#### Your Eleven Labs API key 👇",
placeholder="Paste your Eleven Labs API key",
type="password")
set_api_key(user_api_key)
#container for the chat history
response_container = st.container()
#container for the user's text input
container = st.container()
with container:
with st.form(key='my_form', clear_on_submit=True):
audio_file = st.file_uploader("Upload an audio file ", type=[ "wav,Mp4","Mp3"])
submit_button = st.form_submit_button(label='Send')
if audio_file is not None and submit_button :
output_file_path = "./output_audio.mp3"
save_uploaded_file_as_mp3(audio_file,output_file_path )
hindi_input_audio,sample_rate= librosa.load(output_file_path, sr=None, mono=True)
#applying the audio recognition
hindi_transcription=parse_transcription('./output_audio.mp3')
st.success(f"Audio file saved as {output_file_path}")
#convert hindi to english
english_input=hindi_to_english(hindi_transcription)
#feeding the input to the LLM
english_output = conversational_chat(llm_chain,english_input)
#converting english to hindi
hin_output=translate_english_to_hindi(english_output)
#getting the hindi_tts
hindi_output_audio=hindi_tts(hin_output)
# hindi_output_file="./Hindi_output_Audio.Mp3"
# save_uploaded_file_as_mp3(hindi_out"put_audio,hindi_output_file)
st.audio(hindi_output_audio)
st.session_state['past'].append(hindi_input_audio)
st.session_state['generated'].append(hindi_output_audio)
if 'generated' in st.session_state and st.session_state['generated']:
with response_container:
for i in range(len(st.session_state['generated'])):
st.audio(st.session_state["past"][i],format='audio/wav')
st.audio(st.session_state["generated"][i],format='audio/wav')
if __name__ == '__main__':
ui()
|