Open Source · MarkTechPost ·

Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model Transcribing Six Languages via DiffusionGemma’s Parallel Denoising Decoder

Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model Transcribing Six Languages via DiffusionGemma’s Parallel Denoising Decoder

Interfaze open-sourced diffusion-gemma-asr-small, a multilingual speech recognition model that uses diffusion-based decoding rather than autoregression. The system adds audio support to Google’s frozen DiffusionGemma with a about 42M-parameter adapter and can transcribe six languages, with inference cost tied to denois

Read the full story at MarkTechPost →