-
I've been looking into using ARPABET to improve the pronunciation and convergence of TT2. I saw cmudict.py in the text folder; is this integrated into the model's text preprocessing anywhere? I did a…
-
CMU dictionary uses Arpabet but it's directly mapped to IPA. Is that interesting for this project? Or is the scope of this project really the specific focus of representing WIktionary pronunciations i…
twocs updated
7 years ago
-
Statement of intent per current notes to self:
```
# TODO: add rest of TIMIT:
### PAU, EPI, H# lack relevant IPA equivalents
### AX-H, BCL, DCL, GCL, HV, KCL, PCL, TCL are not present here and do…
-
- [ ] Need easily-loaded example data containing ARPAbet (go with SPADE?)
- [ ] Write demonstrations
- [ ] Explain demonstrations
-
Hi,
I am trying to use the DeepFry model with my own dataset.
My data is downsampled to 16k, has TextGrids, and uses the same arpabet phone set.
However, when it is time to write the new TextGr…
evdv updated
3 months ago
-
I have many English texts annotated with ARPABET in the CMU Dictionary.
How can I convert them to the English phone set for this project?
Are there any resources or keywords available?
Thank …
-
I was using the Projects workflow, as I had just upgraded to the Creator tier, and the pronunciation dictionaries do not work the way they are laid out in the documentation. I tried making my own, and…
-
Is there any consensus on best phonetic representation for training TT2? IPA / ARPAbet / etc?
-
Thanks a lot for this amazing and inspiring work. I'm currently working on a Tensor2Tensor like LSTM encoder/decoder G2P, but using the CMU 2 IPA dictionary / alphabet. In your model you are using the…
-
Is the English-language transcription intentional? The International Phonetic Alphabet would be generalizable and more precise.