-
Hi @p0p4k ,
I see that the process time of dac encode in `dev/descript_codec` branch is too slow on CPU in Dataloader. How can we speedup this process?
```
def batched_encodec(self, wav):
…
-
"Style": "h1"
Should not be "style", a heading is not a style, it's a semantic label for type of content in the text node. This property seems to have a confusing name. Style decoration (this shoul…
-
```
Add SSML support for capable TTS engines. Need a list of SSML-capable engines.
```
Original issue reported on code.google.com by `web...@gmail.com` on 20 Apr 2012 at 6:19
-
```
Add SSML support for capable TTS engines. Need a list of SSML-capable engines.
```
Original issue reported on code.google.com by `web...@gmail.com` on 20 Apr 2012 at 6:19
-
formed from the pairing session in https://github.com/presciencelabs/tabitha-targets/issues/4#issuecomment-2125655542
-
I know it is quite ackward to do this as the text encoder may produce latent variables which contains pitch, but I'm trying to use the reference linear spectrogram and posterior yingram encoder to gen…
-
I have seen several distillations for different single languages for distil-whisper (like en, de etc). But I have yet to come across some distil-whisper which has been trained to be multilingual. For …
-
Going from open-world to closed-world speech should improve the rate at which sentences can be parsed.
-
Certain lines represent properties of an utterance (e.g. `\txn`, `\sp`), while other lines are properties of words (e.g. `\w`, `\wlt`) or morphemes (e.g. `\m`, `\gl`). Clarify which lines are of which…
-
#
[sound-spaces](https://github.com/facebookresearch/sound-spaces)
[Project: RLR-Audio-Propagation](https://github.com/facebookresearch/rlr-audio-propagation)
[Audio Sensor](https://github.com/f…
yyf17 updated
2 years ago