Fu Guanyu

icon company AliPay icon location HangZhou, China icon location My area of expertise involves multimodal text and speech, including Text-to-Speech, Voice Cloning, Voice Conversion, and Speech & Text LLM models.

Results 1 issues of Fu Guanyu

add function of am streaming inference

12 comment

1. Adding chunk_forward function for FsmnEncoderV2 and MemoryBlockV2 module, which is based on cache and implement streaming inference chunk by chunk; 2. Reconstruct the forward function of KanTtsSAMBERT, extract the...