-
Determine how to tackle the following tasks. It might be helpful to involve SMEs in this early phase to vet the improvisation segments that we're considering. The SMEs will be involved in assessing …
-
Hello!
As Speech to Text models such as Whisper are added having access to some of the impressive AI Text to Speech models would be a nice way to close the loop!
My current suggestion for a model …
-
## ante
#### sona pu
ADJECTIVE different, altered, changed, other
#### sona Linku pi toki Inli
different, altered, changed, other
#### sona Linku pi toki pona
sama ala
#### sona k…
-
-
-
What information should the API expose for "spoken output"?
The text string seems obvious, but is not all that a screen reader can send to the TTS.
For Microsoft Speech API, there's an XML forma…
-
# speech recognition
- Soltau, Hagen, Hank Liao, and Hasim Sak. "Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition." arXiv preprint arXiv:1610.09975 (201…
-
When someone is inside a project or creating a project, they might ask
- [x] what scratch commands are there?
- [x] what are the scratch commands ?
and want to dive deeper
- [x] what's an ex…
-
In blog post, Stage 1 codec has 1kbps bitrate.
```
hertz-codec: a convolutional audio autoencoder that takes mono, 16kHz speech and transforms it into a 8 Hz latent
representation at about 1kbps…
-
Using the google speech recognizer, I get a well-formatted dictionary object when I specify the `show_all=True` option. When I try the same for the sphinx recognizer, it returns a _pocketsphinx_ objec…