YoVDO

Fine-Tuning Whisper for Speech Transcription

Offered By: Trelis Research via YouTube

Tags

Machine Learning Courses LoRA (Low-Rank Adaptation) Courses Performance Evaluation Courses Speech Recognition Courses Audio Transcription Courses Fine-Tuning Courses Hugging Face Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn how to fine-tune Whisper for improved speech transcription in this 49-minute video tutorial from Trelis Research. Explore the process of transcribing YouTube videos using Whisper, gain insights into the inner workings of transcription models, and master the technique of fine-tuning Whisper with LoRA. Evaluate the performance of your fine-tuned model and receive valuable tips for optimizing your speech-to-text projects. Access comprehensive resources, including datasets, slides, and Colab notebooks, to enhance your learning experience and practical implementation.

Syllabus

Fine-tuning speech-to-text models
Video Overview
How to transcribe YouTube videos with Whisper
How do transcription models work?
Fine-tuning Whisper with LoRA
Performance evaluation of fine-tuned Whisper
Final Tips


Taught by

Trelis Research

Related Courses

Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera
Elaborazione del linguaggio naturale
University of Naples Federico II via Federica
Deep Learning for Natural Language Processing
University of Oxford via Independent
Deep Learning Summer School
Independent
Sequence Models
DeepLearning.AI via Coursera