ruslanmv

from IPython.display import FileLink
!tar -czvf lm-evaluation-harness.tar.gz lm-evaluation-harness

def create_download_link(filename):
    return FileLink(filename)

download_link = create_download_link("lm-evaluation-harness.tar.gz")
display(download_link)

ruslanmv

from datasets import load_dataset
from IPython.display import clear_output
import pandas as pd
import re
from dotenv import load_dotenv
import os
from ibm_watson_machine_learning.foundation_models.utils.enums import ModelTypes
from ibm_watson_machine_learning.metanames import GenTextParamsMetaNames as GenParams
from ibm_watson_machine_learning.foundation_models.utils.enums import DecodingMethods
from langchain.llms import WatsonxLLM

ruslanmv

import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
import os
from langchain_google_genai import GoogleGenerativeAIEmbeddings
import google.generativeai as genai
from langchain_community.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate

ruslanmv

# Create a shell script
script_content = f'''
#!/bin/bash
source activate automatic
"$@"
'''
# Write the script to a file
script_filename = 'run'
with open(script_filename, 'w') as script_file:
    script_file.write(script_content)

ruslanmv

import subprocess
import sys
import venv
import os
venv.create("venv", with_pip=True)

ruslanmv

# Create a shell script
script_content = f'''
#!/bin/bash
conda activate {conda_environment_name}
python your_script.py
'''

# Write the script to a file
script_filename = 'activate_and_run.sh'
with open(script_filename, 'w') as script_file:

ruslanmv

import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import HTML
from PIL import Image
from io import BytesIO
import base64

# Read DataFrame
df_path = os.path.join(current_dir, "images","collection.csv")
df = pd.read_csv(df_path)

ruslanmv

To expose the `generate_story_and_speech` function as an API, you can use Flask to create a simple API. Here's an example of how you can do it:

1. Install Flask: `pip install Flask`
2. Create a new file, say `api.py`, and add the following code:

```python
from flask import Flask, request, jsonify
import gradio as gr
from your_module import generate_story_and_speech

ruslanmv

import os
import subprocess
import sys
import shutil

def is_google_colab():
    return 'google.colab' in sys.modules

def is_nvidia_smi_available():
    return shutil.which("nvidia-smi") is not None

ruslanmv

from transformers import VitsModel, AutoTokenizer
import torch
cache_dir = "./cache"  # Specify the current directory as the cache directory
model = VitsModel.from_pretrained("facebook/mms-tts-eng", cache_dir=cache_dir)
tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng", cache_dir=cache_dir)
text = "some example text in the English language"
inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
    output = model(**inputs).waveform