kyutai-labs/delayed-streams-modeling

by kyutai-labs · Toolkits & Frameworks · updated 4mo ago

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

More in Toolkits & Frameworks

FunASR

modelscope

13

Toolkits & Frameworks

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diariza

NeMo

NVIDIA-NeMo

14

Toolkits & Frameworks

A scalable generative AI framework built for researchers and developers working on Large L

sherpa-onnx

k2-fsa

17

Toolkits & Frameworks

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation

pipecat

pipecat-ai

18

Toolkits & Frameworks

Open Source framework for voice and multimodal conversational AI