Instructions to use UsefulSensors/moonshine-streaming-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UsefulSensors/moonshine-streaming-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UsefulSensors/moonshine-streaming-medium")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("UsefulSensors/moonshine-streaming-medium", dtype="auto") - Notebooks
- Google Colab
- Kaggle
GGUF + pure-C++ runtime in CrispASR — Moonshine streaming medium
#4
by cstr - opened
The streaming Moonshine variants run through CrispASR's moonshine-streaming backend (src/moonshine_streaming.cpp) — separate from offline Moonshine because the encoder is sliding-window + raw-waveform.
Same C++ binary, no Python. Auto-detected from GGUF metadata across tiny / small / medium sizes. KV-cached autoregressive decoder.
Pre-quantised GGUFs (MIT): cstr/moonshine-streaming-medium-GGUF
./build/bin/crispasr --backend moonshine-streaming \
-m moonshine-streaming-medium-q4_k.gguf --mic
Sibling sizes: -tiny, -small. Offline siblings at cstr/moonshine-{tiny,base}-GGUF + 6 language variants.