speech

🐸 collection of TTS papers

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

Beginner-friendly AI conversation practice application

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

An open-source model for understanding speech, environmental sounds, and music through captioning, question answering, and reasoning

:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection

语音方向实验室/公司/资源/实习等，欢迎推荐或自荐

A list of publicly available room impulse response datasets and scripts to download them.

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.

Audio samples accompanying publications related to Tacotron, an end-to-end speech synthesis model.

Voice Conversion With Just Nearest Neighbors

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion