Moonshine Streaming Medium -- GGUF

Available variants

Model details

• Architecture: Streaming encoder-decoder ASR. Raw-waveform audio frontend (no mel) + sliding-window transformer encoder (14L, 768d) + autoregressive transformer decoder (14L, 640d, SiLU-gated MLP, partial RoPE)
• Parameters: 245M
• Languages: English
• License: MIT
• Source: UsefulSensors/moonshine-streaming-medium
• Designed for: Low-latency streaming ASR on edge devices

Usage with CrispASR

Notes

• Tokenizer (tokenizer.bin) must be in the same directory as the model file
• Streaming architecture: sliding-window attention with 80ms lookahead
• Audio frontend processes raw waveform (no mel spectrogram needed)

Provenance and EU AI Act Art. 53 note

• Upstream model: UsefulSensors/moonshine-streaming-medium — published by UsefulSensors.
• Upstream licence: mit. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• What was done here: format conversion and/or quantisation only (GGUF/GGML). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
• Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.