Instructions to use nowheel/spazio-npu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use nowheel/spazio-npu with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Spazio 路 modelli per l'NPU
Modelli compilati per il processore neurale (Qualcomm Hexagon HTP v73) dello Snapdragon 8s Gen 4 (SM8735, Nothing Phone 3), usati dall'app Spazio.
parakeet_tdt_0.6b_v3_5s_w8a16_stateful_Qualcomm_SM8735.tflite
Parakeet TDT 0.6B v3 di NVIDIA, dall'export LiteRT di
litert-community/parakeet-tdt-0.6b-v3, quantizzato
con pesi a 8 bit e attivazioni intere a 16 bit (l'HTP di questo chip non accetta fp16) e compilato AOT per SM8735.
Firme uguali al file parakeet_tdt_0.6b_v3_5s_i8_stateful.tflite: encode, decode, decode_1; finestre di 5 s.
Licenza: CC-BY-4.0, come il modello originale di NVIDIA.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
Model tree for nowheel/spazio-npu
Base model
nvidia/parakeet-tdt-0.6b-v3