Summarize YouTube video instantly with the power of distill-whisper and Mixtral-8B
Project description
ytsum
Summarize YouTube videos instantly with the power of distil-whisper and Mixtral-8x7B
ytsum is a Python package that allows you to summarize YouTube videos by leveraging the power of distil-whisper for transcription and Mixtral-8x7B for generating detailed answers based on the video content.
Setup
To use ytsum, you need to get an API key from Together AI.
You can sign up and obtain your API key here: Together AI.
Installation
pip install ytsum
from ytsum import answer_youtube_question, set_together_api_key
# Set your Together AI API key
set_together_api_key("your_together_ai_api_key")
# Example usage
youtube_url = "https://www.youtube.com/watch?v=example"
query = "What is the main topic of this video?"
result = answer_youtube_question(youtube_url, query)
print(result)
Models used
Distil-large-v3: https://huggingface.co/distil-whisper/distil-large-v3
Mixtral-8x7B-SFT: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ytsum-0.1.4.tar.gz.
File metadata
- Download URL: ytsum-0.1.4.tar.gz
- Upload date:
- Size: 4.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
865af8f2cb49c66f49f8d047382375f6619c28e5cf2c52edec04f7e8c2b93f93
|
|
| MD5 |
a2b22a7315ad426550efb861daebce97
|
|
| BLAKE2b-256 |
d341efb5e23c9b189b695df2d464a75076cc61b1dbab975f42f93cfda39871ec
|
File details
Details for the file ytsum-0.1.4-py3-none-any.whl.
File metadata
- Download URL: ytsum-0.1.4-py3-none-any.whl
- Upload date:
- Size: 4.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f2369b221369fa44b6726c4eefc14e2029b9ba3ed90c75c3c64010247d3f32c5
|
|
| MD5 |
5fa3369e103e78e9163d8a91ecb14e77
|
|
| BLAKE2b-256 |
f491386a8a6739e2835c35b54460cd110c30799448b58fcc332ee00209779f0c
|
