MS student @ NTHU EECS. Obsessed with making speech models smaller and faster. Currently poking at codec LMs and streaming ASR.
- Hsinchu, Taiwan
-
08:22
(UTC +06:00)
Highlights
Popular repositories Loading
-
stream-whisper
stream-whisper PublicReal-time streaming ASR built on Whisper with VAD-based chunking and WebSocket support
Python
-
speech-data-pipe
speech-data-pipe PublicEnd-to-end data preparation pipeline for speech LLM training: diarize, filter, codec-tokenize, manifest
Python
-
codec-eval
codec-eval PublicEvaluation toolkit for comparing neural speech codecs (EnCodec, DAC, SpeechTokenizer) across quality, speaker, and ASR metrics
Python
-
-
PSIVG
PSIVG PublicForked from MarkHershey/PSIVG
[CVPR 2026] Physical Simulator In-the-Loop Video Generation
Python
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.