Compare Descript vs. Whisper

This is how you make podcasts. Record. Transcribe. Edit. Mix. It's as easy as typing. Descript gives you complete control over your podcast. Edit text to edit audio. Drag and drop to add music or sound effects. The Timeline Editor allows you to fine-tune your music and volume by adding fades or editing the volume. Both automatic and human-powered transcriptions with industry-leading accuracy and powerful collaboration tools. Automatic transcription is the industry leader with unmatched accuracy. Fast turnaround and only pennies per minute

We have developed and are releasing an open-source neural network named Whisper, which achieves levels of accuracy and resilience in English speech recognition that are comparable to human performance. This automatic speech recognition (ASR) system is trained on an extensive dataset comprising 680,000 hours of multilingual and multitask supervised information gathered from online sources. Our research demonstrates that leveraging such a comprehensive and varied dataset significantly enhances the system's capability to handle different accents, ambient noise, and specialized terminology. Additionally, Whisper facilitates transcription across various languages and provides translation into English from those languages. We are making available both the models and the inference code to support the development of practical applications and to encourage further exploration in the field of robust speech processing. The architecture of Whisper follows a straightforward end-to-end design, utilizing an encoder-decoder Transformer framework. The process begins with dividing the input audio into 30-second segments, which are then transformed into log-Mel spectrograms before being input into the encoder. By making this technology accessible, we aim to foster innovation in speech recognition technologies.