Owner · k2-fsa

k2-fsa

k2-fsa's tracked open-source repos, sorted by stars.

7 repos

#1
sherpa-onnx ↗@k2-fsaC++
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
★ 14,575+95Star change over the last 7 days
#2
OmniVoice ↗@k2-fsaPython
High-Quality Voice Cloning TTS for 600+ Languages
★ 9,641+104Star change over the last 7 days
#3
sherpa-ncnn ↗@k2-fsaC++
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
★ 1,777-1Star change over the last 7 days
#4
icefall ↗@k2-fsaPython
★ 1,484+1Star change over the last 7 days
#5
k2 ↗@k2-fsaCuda
FSA/FST algorithms, differentiable, with PyTorch compatibility.
★ 1,354+2Star change over the last 7 days
#6
ZipVoice ↗@k2-fsaPython
Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
★ 1,053+6Star change over the last 7 days
#7
sherpa ↗@k2-fsaC++
Speech-to-text server framework with next-gen Kaldi
★ 984+4Star change over the last 7 days