ccoreilly

whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

SALMONN

SALMONN: Speech Audio Language Music Open Neural Network

open-lid-dataset

Repository accompanying "An Open Dataset and Model for Language Identification" (Burchell et al., 2023)

webtorrent

⚡️ Streaming torrent client for the web

st-chat

Streamlit Component, for a Chatbot UI

comcast

Simulating shitty network connections so you can build better systems.

whisper-vits-svc

Core Engine of Singing Voice Conversion & Singing Voice Clone

pullcord

Discord archiver

UniAudio

The Open Source Code of UniAudio

whisper-turbo

Cross-Platform, GPU Accelerated Whisper 🏎️

april-asr

Speech-to-text library in C

rapidpages

Generate React and Tailwind components using AI

reckon

Flexibly import bank account CSV files into Ledger for command-line accounting

Matcha-TTS

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

fairseq2

FAIR Sequence Modeling Toolkit 2

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

whisper-edge

OpenAI Whisper for edge devices

SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

lamini

VoiceActivityProjection

Voice Activity Projection Models: Self-supervised learning of Turn-taking Events

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

spear-tts-pytorch

Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

CleanUNet

Official PyTorch Implementation of CleanUNet (ICASSP 2022)

WavJourney

WavJourney: Compositional Audio Creation with LLMs

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

NISQA

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

getTV3Videos

Descarrega vídeos de TV3 (tv3.cat) // Download videos of TV3 channel (tv3.cat)

PolyLangVITS

Multi-speaker Speech Synthesis Using VITS(KO, JA, EN, ZH)

stable-diffusion.cpp

Stable Diffusion in pure C/C++

langstream

Build robust LLM applications with true composability 🔗