Facebook's Wav2Vec using Hugging Face's transformer for Speech Recognition

#datascience #machinelearning #deeplearning

Automatic Speech recognition(ASR) is a task where you automatically extract linguistic text from audio/video files.

Guess what, Facebook AI & Hugging Face are here for our rescue.

Facebook AI recently open sourced the Wav2Vec 2.0 model which helps in Automatic Speech Recognition From 10 Minute Samples & Hugging Face integrated it with Transformers v4.3.0.

In this video, I'll show you how you can utilize the lethal combination of Facebook AI’s Wav2Vec2 & Hugging Face Transformers library to generate text from audio.

I hope you all like it 🙂

https://www.youtube.com/watch?v=Ivz-E2eBUZM

Top comments (0)

Ten Hard Problems in Artificial Intelligence We Must Get Right

Mike Young - Apr 22

Interpretable Graph Neural Networks for Tabular Data

Mike Young - Apr 22

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Mike Young - Apr 22

Vector Databases for generative AI applications

Abhishek Gupta - May 6

DEV Community

Facebook's Wav2Vec using Hugging Face's transformer for Speech Recognition

Top comments (0)

Read next

Ten Hard Problems in Artificial Intelligence We Must Get Right

Interpretable Graph Neural Networks for Tabular Data

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Vector Databases for generative AI applications