ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

all-in-oneasraudio-processingmachine-translationnon-autoregressiveseamlesssimultaneous-translationspeechspeech-enhancementspeech-processing

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 15 months ago.

	Repository	Stars	Language	License	Activity
1	m-bain/whisperXWhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)	★ 24.6k	Python	BSD-2-Clause	Active
2	NVIDIA-NeMo/SpeechA scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automat	★ 18.6k	Python	Apache-2.0	Active
3	speechbrain/speechbrainA PyTorch-based Speech Toolkit	★ 11.9k	Python	Apache-2.0	Active
4	coqui-ai/TTS🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production	★ 46.1k	Python	MPL-2.0	Stale
5	OpenBMB/VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning	★ 39.5k	Python	Apache-2.0	Active
6	google-ai-edge/mediapipeCross-platform, customizable ML solutions for live and streaming media.	★ 37.3k	C++	Apache-2.0	Active
7	babysor/MockingBird🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time	★ 36.9k	Python	Other	Slowing
8	deezer/spleeterDeezer source separation library including pretrained models.	★ 28.5k	Python	MIT	Slowing