Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
Nymbo 
posted an update about 18 hours ago
Post
1031
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.

CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.

See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2

Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
leo-lennox

Me:

  1. Doesn't believe the post
  2. Clicks into the Hugging Face model
  3. Listens to the audio sample
  4. Holy crap no way this is real
  5. Downloads it and realizes it is real.
X-xxx-X

Crazy work bro, this is genuinely so impressive for the model size. This might be THE text-to-speech model of the year.

queenagao430505

This model is really outstanding! The quality of the output when I listened was so good for under 4M. What are you planning on doing next after this model? Are you going to release any follow up for Inflect?
In this post