Downloads · 30 days
0
video-search
tomiwa1a/video-search
video-search is a automatic speech recognition model from tomiwa1a. Use it when you need speech turned into text. It is set up for generic. The card lists the license as gpl-3.0.
This project contains 3 different models that can be used for searching videos.
Access
Public
Updated Feb 13, 2025
Repo size
—
Likes
4
Public
Repo makeup
Click a slice to open those files.
.flac282 KB · 93%
At a glance
- Task
- Automatic Speech Recognition
- Library
- generic
- License
- gpl-3.0
- Access
- Public
- Created
- Dec 24, 2022
- Updated
- Feb 13, 2025
- SHA
- 344b3dea
Model card
From the Hugging Face model README
Video Search
This project contains 3 different models that can be used for searching videos.
- Whisper to convert mp3 files to audio
- BART Sentence Transformer to generate vector embeddings from text
- BART LFQA to generate long form answers given a context
For more context, see: Atlas: Find Anything on Youtube
Inspired by philschmid/openai-whisper-endpoint
- Task
- Automatic Speech Recognition
- Library
- generic
- License
- gpl-3.0
- Created
- Dec 24, 2022
- Updated
- Feb 13, 2025