❤️ Support the channel ❤️
[ Ссылка ]
In this video we walk through the paper Robust Speech Recognition via Large-Scale Weak Supervision, or known as Whisper. The paper brought state of the art results in speech recognition with open source code and weights. You can take a look at the official GitHub repository: [ Ссылка ]. Let me know if a walkthrough on how to use Whisper would be interesting, although there are many other videos on this.
Paid Courses I recommend for learning (affiliate links, no extra cost for you):
⭐ Machine Learning Specialization [ Ссылка ]
⭐ Deep Learning Specialization [ Ссылка ]
📘 MLOps Specialization [ Ссылка ]
📘 GAN Specialization [ Ссылка ]
📘 NLP Specialization [ Ссылка ]
✨ Free Resources that are great:
NLP: [ Ссылка ]
CV: [ Ссылка ]
Deployment: [ Ссылка ]
FastAI: [ Ссылка ]
💻 My Deep Learning Setup and Recording Setup:
[ Ссылка ]
GitHub Repository:
[ Ссылка ]
✅ One-Time Donations:
Paypal: [ Ссылка ]
▶️ You Can Connect with me on:
Twitter - [ Ссылка ]
LinkedIn - [ Ссылка ]
Github - [ Ссылка ]
Timestamps:
0:00 - Introduction
1:27 - Abstract
2:30 - Introduction
8:02 - Dataset collection and processing
10:29 - Model approach
15:25 - Figure of model
20:25 - Experiments and Evaluation
26:17 - Long form transcription, messy :/
28:36 - Model and Dataset scaling
31:25 - Long form transcription (cont), messy :/
32:32 - Ending
