NVIDIA's Parakeet TDT 0.6B v2 Demo
Description
NVIDIA's parakeet-tdt-0.6b-v2 is a 600-million-parameter automatic speech recognition (ASR) model designed for high-quality English transcription, featuring support for punctuation, capitalization, and accurate timestamp prediction. This is a state-of-the-art model ideal for: accurate word-level timestamp predictions, automatic punctuation and capitalization, robust performance on spoken numbers, and song lyrics transcription.
License
The license is comercial friendly:
GOVERNING TERMS: Use of this model is governed by the CC-BY-4.0 license.
Contact
Need help adding transcription to your system? Let's talk!.At RidgeRun.ai we'd love to help.
Links of Interest
Playground
Segments
Words
Characters