modelscope/FunASR

by modelscope · Toolkits & Frameworks · updated 1d ago

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

More in Toolkits & Frameworks

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

PaddleSpeech

PaddlePaddle

19

Toolkits & Frameworks

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR wi