Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces Moonshine v2, an ergodic streaming encoder ASR model designed for latency-critical speech applications, particularly on resource-constrained edge devices. It addresses the latency issues of full-attention Transformer encoders by employing sliding-window self-attention, enabling bounded, low-latency inference while maintaining strong local context. Experiments demonstrate that Moonshine v2 achieves state-of-the-art word error rates on standard benchmarks, matching the accuracy of models six times larger while running significantly faster.
You can now get Transformer-level ASR accuracy with 6x smaller models and dramatically lower latency by using sliding-window self-attention, opening up new possibilities for interactive speech interfaces on edge devices.
Latency-critical speech applications (e.g., live transcription, voice commands, and real-time translation) demand low time-to-first-token (TTFT) and high transcription accuracy, particularly on resource-constrained edge devices. Full-attention Transformer encoders remain a strong accuracy baseline for automatic speech recognition (ASR) because every frame can directly attend to every other frame, which resolves otherwise locally ambiguous acoustics using distant lexical context. However, this global dependency incurs quadratic complexity in sequence length, inducing an inherent"encode-the-whole-utterance"latency profile. For streaming use cases, this causes TTFT to grow linearly with utterance length as the encoder must process the entire prefix before any decoder token can be emitted. To better meet the needs of on-device, streaming ASR use cases we introduce Moonshine v2, an ergodic streaming-encoder ASR model that employs sliding-window self-attention to achieve bounded, low-latency inference while preserving strong local context. Our models achieve state of the art word error rates across standard benchmarks, attaining accuracy on-par with models 6x their size while running significantly faster. These results demonstrate that carefully designed local attention is competitive with the accuracy of full attention at a fraction of the size and latency cost, opening new possibilities for interactive speech interfaces on edge devices.