netease-youdao/Confucius4-R2T2

X2Streaming-ASR is a streaming Automatic Speech Recognition (ASR) system characterized by ultra-low latency and high accuracy.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Optimized Whisper models for streaming and on-device use

Whisper-Flow is a framework designed to enable real-time transcription of audio content using OpenAI’s Whisper model. Rather than processing entire files after upload (“batch mode”), Whisper-Flow accepts a continuous stream of audio chunks and produces incremental transcripts immediately.

Pure C inference of Mistral Voxtral Realtime 4B speech to text model

Faster Whisper transcription with CTranslate2

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.

First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. ⭐**