Loading video...
Video Failed to Load
NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥
330,034 views • 1 year ago •via X (Twitter)
11 Comments

Vaibhav (VB) Srivastav1 year ago
Model checkpoint + voice pack here:

Vaibhav (VB) Srivastav1 year ago
We also added it to TTS Arena, go play with it now:

The Information1 year ago
The best new tech and business podcasts of 2024. Plus, podcasting's $400 million man.

mrfakename1 year ago
Ranking #4 on the TTS Arena above some commercial models 🤯

Vaibhav (VB) Srivastav1 year ago
🔥🔥🔥

Cavit Erginsoy1 year ago
did you say <100 hours?!

Vaibhav (VB) Srivastav1 year ago
yes! synthetic data ftw!

Dyson Dunbar1 year ago
its the first model that has convinced me to switch from xTTS because of the quality. It also helps that its about 10x faster as well on my 3090

Berat1 year ago
<100 hours of audio with 20 epoch. grokking for the win

Vaibhav (VB) Srivastav1 year ago
next step should be to fine-tune on Emilia

Pranjal Soni1 year ago
👀
