Difference between revisions of "FreeNeb Status Report 2017-11-27"

From cslt Wiki
Jump to: navigation, search
Line 53: Line 53:
|Zhenlong Han||
|Zhenlong Han||
* Finish training Japanese acoustic model MPE, but It's get worse along epoch increase. Mengyuan told me that I should tuning all parameters in the Nnet. I will try again with present degs.
* Finish training TDNN with different splice and cnn-tdnn model.
* Finish Uyghur embedded and cloud model xent training. But It is small worse than thuyg20 challenges, both Mengyuan and I dose not know more about the thuyg20 challenges model.
* English embedded model training.
* English embedded model training.
* Uyghur embedded model training.

Revision as of 01:58, 27 November 2017

This Week:

People Last Week This Week Next Week Task Tracing(DeadLine)
Mengyuan Zhao
  • Engineering
  1. Embedded ASR APP.
  2. Set up py-server on our Alibaba cloud server.
  3. Set up py-server on Tom's server.
  4. Draft document for roobo project.
  • Engineering
  1. Try to finish server version of TTS DEMO.
Zhiyong Zhang
  • Fix code bug, and can reproduce the TTS experiment as Doc. Wang scripts based on huilian female1000
  • Large dataset test delayed due to the problems of grid

  • Re-produce the Multi-speaker TTS;
  • To test two hybrid of the speakers.
  • To train duration-model using 16k data.
Yang Wei
  • Finish testing FreeNeb embeded ASR engine
  • Test FreeNeb TTS engine.
Dong Wang
  • OC2017

Zhenlong Han
  • Finish training TDNN with different splice and cnn-tdnn model.
  • English embedded model training.
Shuai Zhang
  • According to the feedback, modify the project.
  • Complete the VVParrot project
  • Add the documents about the two project

Yanchi Jin
  • Complete the megrez_test and already deploied on the server.
  • Start to use the megrez_tool complete same simple structure chart.
  • Complete the interface of megrez_test and the chart of structure.