Instructions to use rithuparan07/ai_summarizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rithuparan07/ai_summarizer with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rithuparan07/ai_summarizer", dtype=torch.bfloat16, device_map="cuda") prompt = "The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct." image = pipe(prompt).images[0] - Transformers
How to use rithuparan07/ai_summarizer with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="rithuparan07/ai_summarizer")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rithuparan07/ai_summarizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| Creating a YouTube video summarizer that works with multiple languages can be approached by adjusting the code and configuration to accommodate various language models and APIs. Below are examples of how you can implement the summarizer in different programming languages, including Python, JavaScript (Node.js), and Java. Each example will use the Hugging Face API to summarize the text after fetching the transcript. | |
| 1. Python Example | |
| python | |
| Copy code | |
| import requests | |
| from youtube_transcript_api import YouTubeTranscriptApi | |
| API_KEY = 'your_huggingface_api_key' | |
| MODEL_ENDPOINT = "https://api-inference.huggingface.co/models/facebook/bart-large-cnn" # Change model as needed | |
| def get_video_id(url): | |
| if "youtube.com" in url: | |
| return url.split("v=")[1].split("&")[0] | |
| elif "youtu.be" in url: | |
| return url.split("/")[-1] | |
| return None | |
| def fetch_transcript(video_id): | |
| try: | |
| transcript = YouTubeTranscriptApi.get_transcript(video_id) | |
| return " ".join([item['text'] for item in transcript]) | |
| except Exception as e: | |
| print(f"Error fetching transcript: {e}") | |
| return None | |
| def summarize_text(text): | |
| headers = { | |
| "Authorization": f"Bearer {API_KEY}", | |
| "Content-Type": "application/json" | |
| } | |
| payload = { | |
| "inputs": text, | |
| "parameters": { | |
| "min_length": 50, | |
| "max_length": 150 | |
| } | |
| } | |
| response = requests.post(MODEL_ENDPOINT, headers=headers, json=payload) | |
| if response.status_code == 200: | |
| return response.json()[0]['summary_text'] | |
| else: | |
| print(f"Error in summarization: {response.status_code} - {response.text}") | |
| return None | |
| def youtube_video_summary(url): | |
| video_id = get_video_id(url) | |
| if not video_id: | |
| print("Invalid YouTube URL") | |
| return None | |
| transcript_text = fetch_transcript(video_id) | |
| if not transcript_text: | |
| print("Could not retrieve transcript.") | |
| return None | |
| return summarize_text(transcript_text) | |
| # Example usage | |
| video_url = "https://www.youtube.com/watch?v=your_video_id" | |
| summary = youtube_video_summary(video_url) | |
| if summary: | |
| print("Summary of the video:") | |
| print(summary) | |
| 2. JavaScript (Node.js) Example | |
| javascript | |
| Copy code | |
| const axios = require('axios'); | |
| const { getTranscript } = require('youtube-transcript-api'); | |
| const API_KEY = 'your_huggingface_api_key'; | |
| const MODEL_ENDPOINT = "https://api-inference.huggingface.co/models/facebook/bart-large-cnn"; // Change model as needed | |
| const getVideoId = (url) => { | |
| const urlParams = new URLSearchParams(new URL(url).search); | |
| return urlParams.get('v') || url.split('/').pop(); | |
| }; | |
| const fetchTranscript = async (videoId) => { | |
| try { | |
| const transcript = await getTranscript(videoId); | |
| return transcript.map(item => item.text).join(' '); | |
| } catch (error) { | |
| console.error('Error fetching transcript:', error); | |
| return null; | |
| } | |
| }; | |
| const summarizeText = async (text) => { | |
| try { | |
| const response = await axios.post(MODEL_ENDPOINT, { | |
| inputs: text, | |
| parameters: { min_length: 50, max_length: 150 } | |
| }, { | |
| headers: { Authorization: `Bearer ${API_KEY}` } | |
| }); | |
| return response.data[0].summary_text; | |
| } catch (error) { | |
| console.error('Error summarizing text:', error); | |
| return null; | |
| } | |
| }; | |
| const youtubeVideoSummary = async (url) => { | |
| const videoId = getVideoId(url); | |
| const transcriptText = await fetchTranscript(videoId); | |
| if (!transcriptText) { | |
| console.log("Could not retrieve transcript."); | |
| return null; | |
| } | |
| const summary = await summarizeText(transcriptText); | |
| return summary; | |
| }; | |
| // Example usage | |
| const videoUrl = "https://www.youtube.com/watch?v=your_video_id"; | |
| youtubeVideoSummary(videoUrl) | |
| .then(summary => { | |
| if (summary) { | |
| console.log("Summary of the video:"); | |
| console.log(summary); | |
| } | |
| }); | |
| 3. Java Example | |
| For Java, you can use libraries like OkHttp for HTTP requests. Ensure you have the required dependencies in your pom.xml if you're using Maven. | |
| xml | |
| Copy code | |
| <dependency> | |
| <groupId>com.squareup.okhttp3</groupId> | |
| <artifactId>okhttp</artifactId> | |
| <version>4.9.1</version> | |
| </dependency> | |
| java | |
| Copy code | |
| import okhttp3.*; | |
| import org.json.JSONArray; | |
| import org.json.JSONObject; | |
| import java.io.IOException; | |
| public class YouTubeSummarizer { | |
| private static final String API_KEY = "your_huggingface_api_key"; | |
| private static final String MODEL_ENDPOINT = "https://api-inference.huggingface.co/models/facebook/bart-large-cnn"; // Change model as needed | |
| public static String getVideoId(String url) { | |
| if (url.contains("youtube.com")) { | |
| return url.split("v=")[1].split("&")[0]; | |
| } else if (url.contains("youtu.be")) { | |
| return url.substring(url.lastIndexOf("/") + 1); | |
| } | |
| return null; | |
| } | |
| public static String fetchTranscript(String videoId) { | |
| // Use any YouTube transcript API or library to fetch the transcript | |
| // This part is simplified; implement based on your chosen method | |
| return "Transcribed text goes here."; | |
| } | |
| public static String summarizeText(String text) throws IOException { | |
| OkHttpClient client = new OkHttpClient(); | |
| RequestBody body = RequestBody.create( | |
| MediaType.parse("application/json"), | |
| new JSONObject() | |
| .put("inputs", text) | |
| .put("parameters", new JSONObject().put("min_length", 50).put("max_length", 150)) | |
| .toString() | |
| ); | |
| Request request = new Request.Builder() | |
| .url(MODEL_ENDPOINT) | |
| .post(body) | |
| .addHeader("Authorization", "Bearer " + API_KEY) | |
| .addHeader("Content-Type", "application/json") | |
| .build(); | |
| Response response = client.newCall(request).execute(); | |
| if (response.isSuccessful()) { | |
| JSONArray jsonArray = new JSONArray(response.body().string()); | |
| return jsonArray.getJSONObject(0).getString("summary_text"); | |
| } else { | |
| System.out.println("Error summarizing text: " + response.code()); | |
| return null; | |
| } | |
| } | |
| public static void main(String[] args) throws IOException { | |
| String videoUrl = "https://www.youtube.com/watch?v=your_video_id"; | |
| String videoId = getVideoId(videoUrl); | |
| String transcriptText = fetchTranscript(videoId); | |
| String summary = summarizeText(transcriptText); | |
| System.out.println("Summary of the video:"); | |
| System.out.println(summary); | |
| } | |
| } | |
| Explanation of Each Example | |
| Python Example: | |
| Uses youtube-transcript-api to fetch transcripts. | |
| Sends the transcript to the Hugging Face API for summarization. | |
| JavaScript (Node.js) Example: | |
| Uses youtube-transcript-api to fetch transcripts. | |
| Sends a POST request to the Hugging Face API to summarize the transcript. | |
| Java Example: | |
| Implements a basic structure to fetch a transcript and summarize it. | |
| Uses OkHttp for HTTP requests. | |
| Notes | |
| API Key: Ensure you replace your_huggingface_api_key with your actual Hugging Face API key in all examples. | |
| Transcript Fetching: The transcript fetching part may require you to use a dedicated service or API. The provided code outlines where to implement this logic. | |
| Model Endpoint: You can change the model endpoint in the code to use different models from Hugging Face that support multi-language summarization, such as models trained specifically for various languages. | |
| These examples give you a foundation for implementing a multi-language YouTube video summarizer in different programming languages. Adjust the fetching and summarization logic as needed based on your requirements and the available libraries or APIs. | |