text_summary = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", torch_dtype=torch.bfloat16) 

 

# model_path = "C:/Users/ankitdwivedi/OneDrive - Adobe/Desktop/NLP Projects/Video to Text Summarization/Model/models--sshleifer--distilbart-cnn-12-6/snapshots/a4f8f3ea906ed274767e9906dbaede7531d660ff" 

 

# text_summary = pipeline("summarization", model=model_path, torch_dtype=torch.bfloat16) 

art video generation model by [Genmo](https://genmo.ai). 

 

https://github.com/user-attachments/assets/4d268d02-906d-4cb0-87cc-f467f1497108 

 

## Overview 

) of text, image, video, and audio and beyond. 

 

 

 

----------- 

Tube Video to Text Summary Tool 

 

This Jupyter Notebook tool transforms YouTube videos into concise text summaries using Whisper and ChatGPT 4. 

 

## Overview 

is a video dataset for 105 different Filipino Sign Language (FSL) signs. 

Each sign is categorized into one of 10 categories and is each represented by approximately 20 four-second video samples. 

Signs were performed by adult deaf FSL signers on a blank blue background and reviewed by an FSL expert. 

 

 

soft Video Description) dataset, which is 

obtained with the help of a machine translation service (Google Translate API). This 

dataset can be used for multimodal video-text tasks, including text-to-video retrieval, 

video-to-text retrieval, and video captioning. Same as the original English dataset, the 

MSVD-Indonesian dataset contains about 80k video-text pairs. 

Tube video to audio 

video = mp.VideoFileClip(link) 

video.audio.write_audiofile("audio.wav") 

 

# Convert speech to text using Google Web Speech API 

tion to convert video to text 

def video_to_text(video_path): 

clip = mp.VideoFileClip(video_path) 

clip.audio.write_audiofile("temp_audio.wav") 

 

tion to transcribe the audio 

def transcribe_video(video_file): 

# Transcribe the audio directly from the video file 

result = model.transcribe(video_file) 

return result['text'] 

Tube video to audio 

video = mp.VideoFileClip(link) 

video.audio.write_audiofile("audio.wav") 

 

# Convert speech to text using Google Web Speech API 

tle('Video to text and then text to speech app') 

 

 

image = st.file_uploader("Upload an image", type=["jpg", "png"]) 

 

ects/Video to Text Summarization/Model/models--distilbert--distilbert-base-uncased-finetuned-sst-2-english/snapshots/714eb0fa89d2f80546fda750413ed43d93601a13") 

#analyzer = pipeline("text-classification", model=model_path) 

# print(analyzer(["This product is good", "This product is expensive"])) 

analyzer = pipeline("text-classification", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english") 

 

ects/Video to Text Summarization/Model/models--deepset--roberta-base-squad2/snapshots/cbf50ba81465d4d8676b8bab348e31835147541b" 

 

# question_answer = pipeline("question-answering", model=model_path) 

question_answer = pipeline("question-answering", model="deepset/roberta-base-squad2") 

 

ects/Video to Text Summarization/Model/models--Salesforce--blip-image-captioning-large/snapshots/2227ac38c9f16105cb0412e7cab4759978a8fd90" 

# caption_image = pipeline("image-to-text", model=model_path) 

caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large") 

# tts_model_path = "C:/Users/ankitdwivedi/OneDrive - Adobe/Desktop/NLP Projects/Video to Text Summarization/Model/models--kakao-enterprise--vits-ljs/snapshots/3bcb8321394f671bd948ebf0d086d694dda95464" 

# Narrator = pipeline("text-to-speech", model=tts_model_path) 

tion to extract audio from a video file  

def extract_audio_from_video(video_file_path, output_format='mp3'):  

try:  

video_clip = VideoFileClip(video_file_path)  

if video_clip.audio is None:  

ult['text'] 

 

with gr.Blocks() as demo: 

gr.HTML( 

""" 

ange to "your-username/the-name-you-picked" 

 

def transcribe(audio): 

text_sv = pipe(audio)["text"] 

print(f"Audio transcribed: {text_sv}") 

ult['text'] 

 

with gr.Blocks() as demo: 

gr.HTML( 

""" 

port texttospeech 

from pydub import AudioSegment 

import requests 

import json 

from langchain_core.output_parsers import StrOutputParser 

tion to convert video to audio 

def video_to_audio(video_file): 

# Load the video using moviepy 

video = mp.VideoFileClip(video_file)