From the course: Hands-On PyTorch Machine Learning
Join today to access over 24,900 courses taught by industry experts.
Torchaudio for audio understanding
From the course: Hands-On PyTorch Machine Learning
Torchaudio for audio understanding
- Now let's continue with a pyrees use case. We would like to transcribe the audio and video lectures into scripts. We'll go through an example using Pie Torch's Torch Audio Library to transcribe some audio speech. This example is provided by Hiro Moto and can be found at the Pie Torch website will be using pre-trained models from web to back 2.0 through Torch Audio. The high level steps of this pipeline includes extract the acoustic features from audio waveform and then estimate the class of the acoustic features framed by frame and then generate hypothesis from the sequence of the class probabilities. Torch audio provides an easy access to the pre-trained weights and associated information such as the expected sample rate and class labels. They're bundled together and available under the Torch Audio dot pipelines module. First, we import map plot lib. Next, we'll create a Wave two VAC two model that performs the feature…
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.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.