Hugging Face's logo
Pano's picture

Pano

Andropano
5
·

AI & ML interests

None yet

Recent Activity

repliedto Nymbo's post 8 days ago
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: https://huggingface.co/owensong/Inflect-Micro-v2 https://huggingface.co/owensong/Inflect-Nano-v2 Try the Demos: https://huggingface.co/spaces/Nymbo/Inflect-TTS (unlimited CPU usage) https://huggingface.co/spaces/owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
reacted to Nymbo's post with 👍 8 days ago
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: https://huggingface.co/owensong/Inflect-Micro-v2 https://huggingface.co/owensong/Inflect-Nano-v2 Try the Demos: https://huggingface.co/spaces/Nymbo/Inflect-TTS (unlimited CPU usage) https://huggingface.co/spaces/owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
liked a model 8 days ago
owensong/Inflect-Micro-v2
View all activity

Organizations

None yet