MycroftAI
/
mimic2
mirror of https://github.com/MycroftAI/mimic2.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Add @MXGray's results to README

pull/2/head
Keith Ito 2017-09-06 21:38:41 -07:00 committed by GitHub
parent 9262f440b2
commit b49b901b82
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -5,10 +5,12 @@ An implementation of Tacotron speech synthesis in TensorFlow.
### Audio Samples ### Audio Samples
* **[Audio Samples](https://keithito.github.io/audio-samples/)** after training for 877k steps (~11 days). * **[Audio Samples](https://keithito.github.io/audio-samples/)** from models trained using this repo.
* Speech started to become intelligble around 20k steps. * The first set was trained for 877K steps on the [LJ Speech Dataset](https://keithito.com/LJ-Speech-Dataset/)
* There hasn't been much improvement since around 200k steps -- loss has gone down, but it's hard to notice * Speech started to become intelligble around 20K steps.
listening to the audio. * Although loss continued to decrease, there wasn't much noticable improvement after ~250K steps.
* The second set was trained by [@MXGray](https://github.com/@MXGray) for 140K steps on the [Nancy Corpus](http://www.cstr.ed.ac.uk/projects/blizzard/2011/lessac_blizzard2011/).
## Background ## Background