[KongchangAI]
Model

FastConformer

An efficient speech recognition encoder architecture proposed by NVIDIA, based on an improved Conformer. It accelerates inference through downsampling and is commonly used in speech recognition and audio processing models.

Timeline (last 90 days)

Nov 3

ufakzeka-kulak is an open-source Turkish speech-to-text model with only 31.6M parameters, using a FastConformer encoder and TDT and CTC heads, trained from scratch, and released under the Apache-2.0 license.

Unverified50%
Oct 12

d1-omni-600M 包含 381M 共享主干加决策头、94M SigLIP2 视觉编码器(来自 LFM2.5-VL-450M)和 112M 17 层 FastConformer 音频编码器。

Unverified50%

All Facts (2)

Source Articles

31.6M-Parameter Turkish Speech Recognition Model: ufakzeka-kulak Open-SourcedNov 3
Liquid d1-omni-600M:树莓派上的多模态决策模型实战Oct 12