Big Data News Hubb
Advertisement
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
Big Data News Hubb
No Result
View All Result
Home Big Data

Introducing Whisper

admin by admin
January 19, 2023
in Big Data


We’ve trained and are open-sourcing a neural net called Whisper that approaches human level robustness and accuracy on English speech recognition.

Read Paper


View Code


View Model Card

Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language. Moreover, it enables transcription in multiple languages, as well as translation from those languages into English. We are open-sourcing models and inference code to serve as a foundation for building useful applications and for further research on robust speech processing.

The Whisper architecture is a simple end-to-end approach, implemented as an encoder-decoder Transformer. Input audio is split into 30-second chunks, converted into a log-Mel spectrogram, and then passed into an encoder. A decoder is trained to predict the corresponding text caption, intermixed with special tokens that direct the single model to perform tasks such as language identification, phrase-level timestamps, multilingual speech transcription, and to-English speech translation.

Other existing approaches frequently use smaller, more closely paired audio-text training datasets, or use broad but unsupervised audio pretraining. Because Whisper was trained on a large and diverse dataset and was not fine-tuned to any specific one, it does not beat models that specialize in LibriSpeech performance, a famously competitive benchmark in speech recognition. However, when we measure Whisper’s zero-shot performance across many diverse datasets we find it is much more robust and makes 50% fewer errors than those models.

About a third of Whisper’s audio dataset is non-English, and it is alternately given the task of transcribing in the original language or translating to English. We find this approach is particularly effective at learning speech to text translation and outperforms the supervised SOTA on CoVoST2 to English translation zero-shot.

We hope Whisper’s high accuracy and ease of use will allow developers to add voice interfaces to a much wider set of applications. Check out the paper, model card, and code to learn more details and to try out Whisper.



Source link

Previous Post

New Practices in Data Governance and Data Fabric for Telecommunications

Next Post

How to Protect Company’s Sensitive Information From Outsiders

Next Post

How to Protect Company’s Sensitive Information From Outsiders

Recommended

Tomorrow’s Tech: What Does the Future of Analytics Look Like?  

October 16, 2022

Video Highlights: Modernize your IBM Mainframe & Netezza With Databricks Lakehouse

November 3, 2022

Microsoft Puts AI into ERP and CRM

March 11, 2023

Don't miss it

Big Data

“Above the Trend Line” – Your Industry Rumor Central for 9/29/2023

September 30, 2023
Big Data

Ballard Power Systems RDU (Remote Diagnostics Unit) Visualization Platform for Interactive At-Scale Industrial IoT Streaming Analytics

September 30, 2023
News

Process and analyze highly nested and large XML files using AWS Glue and Amazon Athena

September 30, 2023
News

Rethinking ‘Open’ for AI

September 30, 2023
News

Embracing the New Era of Online Education

September 30, 2023
Big Data

Unleashing the Power of AI in Paid Search Marketing: Insights from Industry Expert

September 29, 2023
big-data-footer-white

© Big Data News Hubb All rights reserved.

Use of these names, logos, and brands does not imply endorsement unless specified. By using this site, you agree to the Privacy Policy and Terms & Conditions.

Navigate Site

  • Home
  • Big Data
  • News
  • Contact us

Newsletter Sign Up

No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us

© 2022 Big Data News Hubb All rights reserved.