ccoreilly

llama2.c

Inference Llama 2 in one file of pure C

vits_chinese

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

vall-e

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

ggml

Tensor library for machine learning

dp-rewrite

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

wgpu-tensor

laserbeak

Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU

datadm

DataDM is your private data assistant. Slide into your data's DMs

umx.cpp

C++17 port of Open-Unmix-PyTorch with streaming LSTM inference, ggml, quantization, and Eigen

vanmoof-encryption-key-exporter

Export all bike details (such as encryption key) of your VanMoof bikes.

tinydiarize

Minimal extension of OpenAI's Whisper adding speaker diarization with special tokens

telegram_media_downloader

Download media files from a telegram conversation/chat/channel up to 2GiB per file

piping-ssh-web

SSH over HTTPS via Piping Server on Web browser

piping-server

Infinitely transfer between every device over pure HTTP with pipes or browsers

go-webrtc-piping

WebRTC P2P tunneling/duplex with Piping Server WebRTC signaling

willow

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

willow-inference-server

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

actinia-core

Actinia Core is an open source REST API for scalable, distributed, high performance processing of geographical data that uses mainly GRASS GIS for computational tasks (DOI: https://doi.org/10.5281/zenodo.5879231) | Tutorial: https://actinia-org.github.io/actinia-core/ | Docker: https://hub.docker.com/r/mundialis/actinia-core

INTERSPEECH-2023-Papers

INTERSPEECH 2023 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023 conference. Explore the latest advances in speech and language processing. Code included. Star the repository to support the advancement of speech technology!

NoRefER

toxiproxy

:alarm_clock: :fire: A TCP proxy to simulate network and system conditions for chaos and resiliency testing

rebel

REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).

survey

A Survey on Neural Speech Synthesis https://arxiv.org/pdf/2106.15561.pdf

WhisperBiasing

basic-pitch

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

DeepFilterNet

Noise supression using deep filtering

noise-repellent

Lv2 suite of plugins for broadband noise reduction

open-archaeo

A list of open source archaeological software and resources

Auto_Tuning_Zeroshot_TTS_and_VC

Official implementation of "Automatic Tuning of Loss Trade-offs without Hyper-parameter Search in End-to-End Zero-Shot Speech Synthesis", Interspeech 2023

zm-text-tts

[IJCAI'23] Learning to Speak from Text for Low-Resource TTS