From the course: Building a Project with the ChatGPT API
Unlock the full course today
Join today to access over 24,700 courses taught by industry experts.
Turn audio into text using Whisper - ChatGPT Tutorial
From the course: Building a Project with the ChatGPT API
Turn audio into text using Whisper
- Do you want to learn about the most robust and accurate automatic speech recognition system on the planet? We're talking about a model trained on 680,000 hours of multilingual and multitask data collected from the web. Through Open AI's whisper APIs, you can turn audio or speech into text. It provides easy access to the open source text to speech whisper model. The model takes in an audio file and performs transcriptions, which enables translation in multiple languages and from those languages into English. Whisper accepts certain input file types like MP3 or MP4 and others. There are nine models in the Whisper family to choose from, with different sizes and capabilities available. The Whisper model is a transformer based encoder decoder model, also called a sequence to sequence model. I encourage you to pause this video and learn more about sequence to sequence learning to deepen your understanding of machine…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
Create chatbots using chat completion4m 34s
-
Generate text using text completion3m 34s
-
(Locked)
Measure relatedness using embeddings4m 26s
-
(Locked)
Turn audio into text using Whisper3m 46s
-
(Locked)
Generate images using DALL-E5m 25s
-
(Locked)
Customize a model using fine-tuning6m 52s
-
(Locked)
Examine key concepts3m 43s
-
(Locked)
Understand pricing models2m 52s
-
-
-
-
-
-
-
-
-