Open AI's Whisper Is Amazing
Offered By: sentdex via YouTube
Course Description
Overview
Explore OpenAI's Whisper, a groundbreaking speech-to-text model capable of transcribing and translating 97 languages. Learn about its weakly supervised encoder-decoder transformer architecture, trained on 680,000 hours of audio. Discover the model's implementation, fine-tuning process, and multitask capabilities. Delve into topics such as data quality, pipeline structure, generalization, overfitting prevention, and the impact of model size on performance. Gain insights into the weekly supervise technique and how mixing tasks contributes to the model's versatility.
Syllabus
Intro
What is Whisper
Example Implementation
Weekly supervise
Finetuning
Mixing Tasks
Data Quality
Model
Pipeline
Generalization
Overfitting
Model size
Multitask performance
Taught by
sentdex
Related Courses
Facebook: Product Optimization with Adaptive Experimentation - F8 2019Meta via YouTube Improving Conversational AI - Advancements in NLP Research at Facebook
Meta via YouTube SILCO: Show a Few Images, Localize the Common Object
University of Central Florida via YouTube Annotation-Efficient Object Detection: Unsupervised Discovery to Active Learning
VinAI via YouTube Continual Learning: Adapting Machine Learning to an Evolving World
VinAI via YouTube