flâneur

Tincans - Final Technical Report

tincans.ai · 2,510 words · saved by 1 readers

This post describes Tincans' research in pursuit of a real-time AI voice system, largely performed from January to April 2024. We detail four main contributions and release code for each component. We demonstrated the first two components in April 2024, with a demo of sub-500ms AI voice chat on consumer hardware. At the time, it was the fastest public system. The previously undisclosed components are parts of an overall voice chat system capable of real-time duplex chat. The components can be tuned and created cheaply, leveraging existing pretrained models. Constraints breed creativity; we hope that these techniques and code offer inspiration to others. Looking for software engineering roles? Practice interviewing and get a better job with Parahack, the world's best AI tutor! Gazelle is a joint speech-language model which accepts audio natively. We have previously documented it, see our architecture announcement and model release. We also previously opensourced checkpoints and code. He

Tincans - Final Technical Report Tincans Final Technical Report Chris Hua | 2024-09-16 This post describes Tincans' research in pursuit of a real-time AI voice system, largely performed from January to April 2024. We detail four main contributions and release code for each component. Joint speech-language model (Gazelle) Real-time orchestration framework (Gondola) Integrated turn-taking and backchannel prediction model Amortized prefill We demonstrated the first two components in April 2024, with a demo of sub-500ms AI voice chat on consumer hardware. At the time, it was the fastest public sys

saved by

related reading