[Server] fix server doc and decode_method

[tts] normalize wav max value to 1 in preprocess, test=tts

[doc]add streaming tts demo, test=doc

[server] improve code

[server]change vector train.py local_rank to rank

[CLI] Add cacu rtf scripts

speedyspeech support kunlun

[server]streaming asr server using paddlespeech_server/client

[ASR] Replace dist.spawn with dist.launch

[server]update the vector and text readme

[CLI]Add RTF wrapper for asr.