Upgrading Kokoro: natural TTS for short bursts
•
26
Hexgrad PRO
hexgrad
AI & ML interests
Not pregnant, but always delivers
Recent Activity
updated
a model
16 minutes ago
hexgrad/Kokoro-82M
new activity
about 1 hour ago
hexgrad/Kokoro-82M:Error with the new version
new activity
about 1 hour ago
hexgrad/Kokoro-82M:Request to Release v0.23 Model with Chinese Support
Articles
Organizations
None yet
hexgrad's activity
updated
a
model
16 minutes ago
Error with the new version
1
#84 opened about 9 hours ago
by
andykaufseo
Request to Release v0.23 Model with Chinese Support
1
#83 opened about 17 hours ago
by
officialayang
有没有跟这个模型速度差不多的中文语音模型。这个模型太给力了，就是不支持中文
6
#46 opened 14 days ago
by
xl343
Will Version 1.0 support Chinese (Mandarin)?
1
#85 opened about 7 hours ago
by
hanswang1973
[Rule] Try on Colab before posting a technical issue
4
#45 opened 14 days ago
by
hexgrad
updated
a
Space
1 day ago
Permissively licensed transcription to International Phonetic Alphabet (IPA) in Python
6
#50 opened 13 days ago
by
davidmezzetti
More technical information
2
#27 opened 20 days ago
by
cduk
E-MOBI / EKONOMIK MOBIL
#81 opened 2 days ago
by
jesus-christ666
updated
2
models
3 days ago
published
a
model
3 days ago
updated
2
datasets
3 days ago
Good
#78 opened 4 days ago
by
Mickel96292
generate_full is cut unexpectedly.
4
#70 opened 8 days ago
by
konecth
posted
an
update
5 days ago
Post
3136
IMHO, being able & willing to defeat CAPTCHA, hCaptcha, or any other reasoning puzzle is a must-have for any Web-Browsing / Computer-Using Agent (WB/CUA).
I realize it subverts the purpose of CAPTCHA, but I do not think you can claim to be building AGI/agents without smoothly passing humanity checks. It would be like getting in a self-driving car that requires human intervention over speed bumps. Claiming AGI or even "somewhat powerful AI" seems hollow if you are halted by a mere CAPTCHA.
I imagine OpenAI's Operator is *able* but *not willing* to defeat CAPTCHA. Like their non-profit status, I expect that policy to evolve over time—and if not, rival agent-builders will attack that opening to offer a better product.
I realize it subverts the purpose of CAPTCHA, but I do not think you can claim to be building AGI/agents without smoothly passing humanity checks. It would be like getting in a self-driving car that requires human intervention over speed bumps. Claiming AGI or even "somewhat powerful AI" seems hollow if you are halted by a mere CAPTCHA.
I imagine OpenAI's Operator is *able* but *not willing* to defeat CAPTCHA. Like their non-profit status, I expect that policy to evolve over time—and if not, rival agent-builders will attack that opening to offer a better product.
- 2 replies
[Status] Jan 21 Update
51
#36 opened 17 days ago
by
hexgrad
updated
a
model
5 days ago