Moonshine Tiny BF16 Torq

--- library_name: torq tags: - Automatic Speech Recognition - Astra SL - SL2600 - MPU license: mit base_model: - Synaptics/Moonshine base_model_relation: quantized --- # Moonshine Tiny ## Model Overview Moonshine is a high-efficiency automatic speech recognition (ASR) model designed specifically for real-time speech recognition. Unlike Whisper, which processes audio in fixed 30-second chunks, Moonshine uses a variable-length architecture that only computes the actual duration of the speech received. Useful Sensors developed Moonshine and released the English model as open-source. There are 2 models of different sizes and capabilities - base and tiny. The tiny version utilizes 27M parameters. ## Model Features - **Model Type:** Automatic Speech Recognition - **Input:** Raw waveform (1D array of floats) 16kHz mono audio up to 30 seconds - **Output:** Sequence of token IDs (integers) - **Quantization**: None ## Recommended Platforms - Synaptics AstraTM SL2600-Series with Torq - Synaptics AstraTM SL1600-Series with Synap ## Metrics | Platform | Model / Stage | Environment | Inference Time | Infer / s | | --------- | --------- | --------- | --------- | --------- | | SL2610 | Moonshine Tiny Decoder | Torq v2.0.0 | 15.6 | 64.1 | | SL2610 | Moonshine Tiny Encoder (5 sec audio) | Torq v2.0.0 | 156.1 | 6.4 ## Deployment ### Compiled Models Torq compiled model files are provided in this repository. To recompile the models, see the [Torq Documentation](https://synaptics-torq.github.io/torq-compiler/v/latest/). ### Source Models The source model files are available at [Synaptics/Moonshine](https://huggingface.co/Synaptics/Moonshine). ### Usage Tutorials / Example Apps Synaptics AI Developer Zone Tutorials - [SL2600-Series Speech-To-Text Tutorial](https://developer.synaptics.com/docs/sl/sl2600/introduction) - [SL1600-Series Speech-To-Text Tutorial](https://developer.synaptics.com/docs/sl/sl1600/getting-started/speech-to-text#useful-sensorss-moonshine) Example App GitHub Repositories - [Torq Examples](https://github.com/synaptics-torq/torq-examples): Basic model usage examples for Torq - [SL2610 Examples](https://github.com/synaptics-astra-demos/sl2610-examples): Interactive examples for SL2610-Series ## License Both the source model and the compiled model for on-device deployment are licensed under [MIT License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md). ## Learn More - [Synaptics AI Developer Zone](https://developer.synaptics.com?utm_source=hf): Get started with documentation, tutorials and resources for your Edge AI journey. - [Astra Support Portal](https://synacsm.atlassian.net/servicedesk/customer/portal/543?utm_source=hf): Connect with our engineering team and community.