Instructions to use UsefulSensors/moonshine-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UsefulSensors/moonshine-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UsefulSensors/moonshine-tiny")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("UsefulSensors/moonshine-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("UsefulSensors/moonshine-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Android + OpenCL implementation β runs on-device on non-flagship phones (Adreno 6xx)
#9
by a8nova - opened
Hi! I wanted to share an Android + OpenCL implementation of Moonshine-tiny, in case anyone wants to run it on a phone:
- Try it: Edgi on Google Play β runs fully on-device, no cloud.
- Open source: the app is built on top of the open-source adreno-llms inference engine β https://github.com/a8nova/adreno-llms β pure C++/OpenCL with hand-written kernels tuned for Adreno, taking the raw 16 kHz waveform in directly (no mel stage).
It's tuned and tested on Adreno 6xx GPUs β the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) β and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it transcribes at RTF ~0.3 one-shot (including TTFT), token-exact vs the PyTorch reference on the verification clips.
Hope it's useful β happy to answer questions!