A ggml (C ) re-implementation of tortoise-tts

A collection of tools, libraries, and tests for Vulkan shader compilation.

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, L…

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 …

Port of Funasr's Paraformer model in C/C

ggml implementation of embedding models including SentenceTransformer and BGE

An Open Source text-to-speech system built by inverting Whisper.

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose : Vision Transformer for Generic Body Pose Estimation"

Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

🦜🔗 Build context-aware reasoning applications

Inference Llama 2 in one file of pure C

用于从头预训练 SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Inference Llama 2 in one file of pure Python

simplify the duckling and just for zh

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

Fast inference engine for Transformer models

ggml implementation of BERT

Pybind11 bindings for Whisper.cpp

Python bindings for whisper.cpp

Custom Intent Classification Model with Rasa

Android Chinese TTS Engine Base On Tensorflow TTS , use for TfLite Models Test。安卓离线中文TTS引擎，在TensorflowTTS基础上开发，用于TfLite模型测试。

Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei and aishell3 datasets

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"