Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from textblob import TextBlob | |
| from langchain.document_loaders import TextLoader #for textfiles | |
| from langchain.text_splitter import CharacterTextSplitter #text splitter | |
| from langchain.embeddings import HuggingFaceEmbeddings #for using HugginFace models | |
| from langchain.vectorstores import FAISS #facebook vectorizationfrom langchain.chains.question_answering import load_qa_chain | |
| from langchain.chains.question_answering import load_qa_chain | |
| from langchain import HuggingFaceHub | |
| import rich | |
| from rich.console import Console | |
| from rich.panel import Panel | |
| from rich import print | |
| from langchain.document_loaders import TextLoader | |
| # text splitter for create chunks | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain.chains.summarize import load_summarize_chain | |
| import datetime | |
| def You_sum(text): | |
| url = input("Enter the url of video you want summary of") | |
| print(myvideo.title) | |
| print(myvideo.captions) | |
| code = input("Enter the code you want: ") | |
| print("Scraping subtitiles....") | |
| sub = myvideo.captions[code] | |
| #downloading the files in SRT format | |
| caption = sub.generate_srt_captions() | |
| def clean_sub(sub_list): | |
| lines = sub_list | |
| text = '' | |
| for line in lines: | |
| if re.search('^[0-9]+$', line) is None and re.search('^[0-9]{2}:[0-9]{2}:[0-9]{2}', line) is None and re.search('^$', line) is None: | |
| text += ' ' + line.rstrip('\n') | |
| text = text.lstrip() | |
| #print(text) | |
| return text | |
| print("transform subtitles to text: ") | |
| srt_list = str(caption).split("\n") #generates a list of all the lines | |
| final_text = clean_sub(srt_list) | |
| doc = summarization_text | |
| summaries = [] | |
| text_splitter = RecursiveCharacterTextSplitter( | |
| # Set a really small chunk size, just to show. | |
| chunk_size = 2500, | |
| chunk_overlap = 20, | |
| length_function = len, | |
| ) | |
| texts = text_splitter.create_documents([doc]) | |
| #print(texts) | |
| # Call the Hugging Face API to run the Summarization Chain | |
| llm_id = 'MBZUAI/LaMini-T5-223M' | |
| import datetime | |
| summaries = [] | |
| start = datetime.datetime.now() #not used now but useful | |
| console.print("[yellow bold] Inizializing Summarization Chain") | |
| # Call the Chain and run it | |
| llm=HuggingFaceHub(repo_id=llm_id, model_kwargs={"temperature":1, "max_length":23000}) | |
| chain = load_summarize_chain(llm, chain_type="map_reduce") | |
| summary = chain.run(texts) | |
| summaries.append(summary) | |
| # print the results with rich text format | |
| console.print("[bold green]Summary for: ", myvideo.title) | |
| console.print(f"[italic black] with {llm_id} \n") | |
| # calculate the elapsed time and print to a Rich Console | |
| stop = datetime.datetime.now() #not used now but useful | |
| delta = stop-start | |
| print(Panel(str(summaries[0]), title='AI Summarization')) | |
| console.print(f"[red bold]Summarization completed in {delta}") | |
| iface = gr.Interface(fn=You_sum, inputs="text", outputs="text") | |
| iface.launch() |