A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

The Memory layer for your AI apps

Enforce the output format (JSON Schema, Regex etc) of a language model

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Implementation for MatMul-free LM.

Search for words, documents, images, videos, news, maps and text translation using the DuckDuckGo.com search engine. Downloading files and images to a local hard drive.

Instruct-tune LLaMA on consumer hardware

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

Tuning and Evaluation of RAG pipeline. (Automated optimization to be added soon)

Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.

LlamaIndex is a data framework for your LLM applications

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

Inference code for CodeLlama models

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

SoftVC VITS Singing Voice Conversion

Core Engine of Singing Voice Conversion & Singing Voice Clone

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor

Inference code for Llama models

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

Official Code for DragGAN (SIGGRAPH 2023)

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Identification and conversion functions for Chinese text processing

List of speech synthesis papers.

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）