k2-fsa

non-profit

https://github.com/k2-fsa/

AI & ML interests

FSA/FST algorithms, differentiable, with PyTorch compatibility. Automatic speech recognition

Recent Activity

csukuangfj updated a model about 2 hours ago

k2-fsa/sherpa-onnx-zipformer-gigaspeech-2023-12-12

csukuangfj updated a Space 3 days ago

k2-fsa/automatic-speech-recognition

yfyeung authored a paper 4 days ago

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

View all activity

updated a model about 2 hours ago

k2-fsa/sherpa-onnx-zipformer-gigaspeech-2023-12-12

Updated about 2 hours ago • 4

updated a Space 3 days ago

Automatic Speech Recognition

Transcribe speech from audio files, mic, or URLs

authored a paper 4 days ago

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

Paper • 2611.02476 • Published 6 days ago • 3

submitted a paper to Daily Papers 5 days ago

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

Paper • 2611.02476 • Published 6 days ago • 3

authored a paper 11 days ago

Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams

Paper • 2610.35439 • Published 14 days ago • 15

updated a model 11 days ago

k2-fsa/sherpa-onnx-zipformer-audio-tagging-2024-04-09

Updated 11 days ago • 1

updated a Space 13 days ago

Wasm Speech Enhancement Gtcrn

WebAssembly speech enhancement

updated 2 Spaces 16 days ago

Web Assembly Ten Vad Sherpa Onnx

Detect when you’re speaking in real time using your browser

Web Assembly Vad Sherpa Onnx

Detect speech segments in real-time using your browser

updated a model 30 days ago

k2-fsa/ZipVoice

Text-to-Speech • Updated 30 days ago • 65

authored a paper about 1 month ago

Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training

Paper • 2609.33645 • Published Sep 27 • 4

submitted a paper to Daily Papers about 1 month ago

Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training

Paper • 2609.33645 • Published Sep 27 • 4

authored a paper about 2 months ago

Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction

Paper • 2609.21392 • Published Sep 18

in k2-fsa/OmniVoice about 2 months ago

Request for Clarification and Update Regarding OmniVoice Model License for Commercial Use

#37 opened about 2 months ago by

dibyajyotimishra

authored a paper 4 months ago

GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark

Paper • 2606.28884 • Published Jun 27 • 2

authored 4 papers 5 months ago

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

Paper • 2506.13053 • Published Jun 16, 2025

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

Paper • 2507.09318 • Published Jul 12, 2025 • 2

CR-CTC: Consistency regularization on CTC for improved speech recognition

Paper • 2410.05101 • Published Oct 7, 2024

OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Paper • 2604.00688 • Published Apr 1 • 18

authored a paper 5 months ago

MMAE: A Massive Multitask Audio Editing Benchmark

Paper • 2606.07229 • Published Jun 5 • 45