| license: other | |
| license_name: nvidia-open-model-license | |
| license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf | |
| base_model: nvidia/nemotron-speech-streaming-en-0.6b | |
| tags: | |
| - coreml | |
| - automatic-speech-recognition | |
| - streaming | |
| # Murmur ASR — Nemotron streaming CoreML | |
| CoreML conversion of | |
| [nvidia/nemotron-speech-streaming-en-0.6b](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) | |
| packaged for the Murmur dictation app: 160 ms streaming chunks, | |
| encoder/decoder/joint/preprocessor `.mlmodelc` bundles plus tokenizer and | |
| metadata, zipped for direct download. | |
| - `nemotron-160ms.zip` — the model bundle Murmur unpacks at first launch | |
| - `nemotron-160ms.zip.sha256` — checksum, verified by the app before unpacking | |
| Base model by NVIDIA, redistributed under the NVIDIA Open Model License | |
| (see license link). Conversion is mechanical; no weights were modified. | |