I may be slow to respond.
Speech recognition/synthesis
-
Northwestern Polytechnical University
- Suzhou
-
16:07
(UTC +08:00)
Stars
ASR
5 repositories
Faster Whisper transcription with CTranslate2
Multilingual Voice Understanding Model
We Speech Transcript based on LLM, in 300 lines of code.
Text to speech alignment using CTC forced alignment