🏆 #1,216 overall#143 of 795 in Speech Recognition

ictnlp /StreamSpeech

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

$ git clone https://github.com/ictnlp/StreamSpeech.git
GitHub social preview for ictnlp/StreamSpeech
Stars
1.3K
1,292
This week
-1 ★
Forks
105
105
Language
Python
License
MIT
Created
Jun 4, 2024
2.5 years old
Last push
Jun 29, 2025

Stars, last 17 days

Oct 28, 2026 → Nov 16, 2026
★ 1.3K▼ 1★ 1.3K

Categories

GitHub topics

More in Speech Recognition

Speech Recognition

nyrahealth/CrisperWhisper🔥 active

▲ +14 ★ this week

Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.

PythonOtherupdated Nov 11, 2026
GitHub ↗★ 1.5K⑂ 97
Speech Recognition

NVIDIA-NeMo/Speech🔥 active

▲ +43 ★ this week

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

🌍 Machine Translation
PythonApache-2.0updated Nov 16, 2026
GitHub ↗★ 18.8K⑂ 3.7K
Speech Recognition

espnet/espnet🔥 active

▲ +8 ★ this week

End-to-End Speech Processing Toolkit

🌍 Machine Translation
PythonApache-2.0updated Nov 16, 2026
GitHub ↗★ 10K⑂ 2.5K
Speech Recognition

tensorflow/lingvo

Lingvo

🌍 Machine Translation🤖 Language Models🧠 Natural Language Processing
PythonApache-2.0updated Oct 29, 2026
GitHub ↗★ 2.9K⑂ 451

Data from GitHub · snapshot Nov 16, 2026