Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
boxed
4 months ago
|
parent
|
context
|
favorite
| on:
Generate audiobooks from E-books with Kokoro-82M
Some of those samples sound like they are emoting in Korean while speaking English.
lyu07282
4 months ago
[–]
True, maybe an artifact of the training data, here is another one:
https://www.microsoft.com/en-us/research/project/emoctrl-tts...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
