Zipformer: A faster and better encoder for automatic speech recognition
Paper β’ 2310.11230 β’ Published β’ 1
fangjun
csukuangfj
AI & ML interests
None yet
Recent Activity
updated a model 5 days ago
csukuangfj/sherpa-onnx-rknn-models updated a Space 11 days ago
k2-fsa/text-to-speech updated a model 14 days ago
csukuangfj/sherpa-onnx-tts-samplesOrganizations
authored 11
papers 6 months ago
PromptASR for contextualized ASR with controllable style
Paper β’ 2309.07414 β’ Published
Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context
Paper β’ 2309.08105 β’ Published β’ 1
Pruned RNN-T for fast, memory-efficient ASR training
Paper β’ 2206.13236 β’ Published
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation
Paper β’ 2211.00508 β’ Published
Blank-regularized CTC for Frame Skipping in Neural Transducer
Paper β’ 2305.11558 β’ Published
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
Paper β’ 2409.00819 β’ Published
Delay-penalized CTC implemented based on Finite State Transducer
Paper β’ 2305.11539 β’ Published
k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning
Paper β’ 2411.17100 β’ Published
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
Paper β’ 2506.13053 β’ Published
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
Paper β’ 2507.09318 β’ Published β’ 2