Skip to content
trckr.ai

Loading…

The archive

All releases

Every model release from the labs trckr follows, newest first: spotted live since November 2026, and from the archive back to 2018.

RSS for this view
Reset

December 2023

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

SeamlessM4T

November 2023

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

MultiBand Diffusion

June 2023

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

MusicGen

March 2023

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

AudioGen

October 2022

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

EnCodec

January 2022

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

data2vec (speech)

July 2021

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

HuBERT

October 2020

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

wave2vec 2.0 LARGE

November 2019

MetaVoice & audio

NotableNotable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.OpenOpen model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

Transformer - LibriVox + Decoding/Rescoring

Free alerts

Know the moment a new model drops.

Pick one or several. Each has its own settings for what you hear about.