marty1885 / paroli
Streaming TTS based on Piper with optional RK3588 NPU support
☆79Updated 4 months ago
Alternatives and similar repositories for paroli:
Users that are interested in paroli are comparing it to the libraries listed below
- My develoopment fork of llama.cpp. For now working on RK3588 NPU and Tenstorrent backend☆90Updated 2 weeks ago
- Run Large Language Models on RK3588 with GPU-acceleration☆97Updated last year
- Easier usage of LLMs in Rockchip's NPU on SBCs like Orange Pi 5 and Radxa Rock 5 series☆126Updated last month
- Efficient Inference of Transformer models☆432Updated 8 months ago
- Reverse engineering the rk3588 npu☆77Updated 10 months ago
- Experiments to test different speech recognition systems for SEPIA Framework☆60Updated last year
- Allows access via HTTP to LLM running on RK3588 NPU. Returns JSON response.☆21Updated 10 months ago
- ☆721Updated last week
- Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU…☆123Updated this week
- Automated script to convert Huggingface and GGUF models to rkllm format for running on Rockchip NPU☆29Updated 5 months ago
- Port of Funasr's Sense-voice model in C/C++☆326Updated last week
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆62Updated this week
- A lightweight pure C++ Text-to-Speech (TTS) pipeline with OpenVINO, supporting multiple languages.☆51Updated this week
- A ggml (C++) re-implementation of tortoise-tts☆178Updated 7 months ago
- Demonstration of running a native LLM on Android device.☆129Updated this week
- ncnn benchmark on various single board computers☆160Updated last year
- Snowboy reimplementation☆84Updated 2 years ago
- ONNX implementation of Whisper. PyTorch free.☆92Updated 4 months ago
- Run generative AI models in sophgo BM1684X☆196Updated this week
- rkllm_talking is a standalone compiled voice communication system based on a large model || rkllm_talking 是一个独立编译的基于大模…☆11Updated 6 months ago
- Generate samples using Piper to train wake word models☆31Updated last year
- Running the F5-TTS by ONNX Runtime☆147Updated last week
- ONNX Inference of Pyannote Segmentation☆84Updated 3 months ago
- Explore LLM model deployment based on AXera's AI chips☆99Updated 2 weeks ago
- A project that optimizes Whisper for low latency inference using NVIDIA TensorRT☆79Updated 6 months ago
- 一个模块化,全过程可离线,低占用率的对话机器人/智能音箱☆67Updated last month
- Speech-to-text server framework with next-gen Kaldi☆660Updated 2 weeks ago
- Useful resources for developing with the RK3588.☆277Updated 4 months ago
- 端到端语音唤醒工具箱,从模型训练到模型推理。☆112Updated 7 months ago
- OpenAI Whisper for edge devices☆124Updated 2 years ago