Inflect v2
Collection
Complete local text-to-waveform speech models at 3.96M and 9.36M parameters, with official PyTorch and ONNX Runtime releases. • 5 items • Updated • 5
queena gao
queenagao430505
·
AI & ML interests
None yet
Recent Activity
upvoted a collection 36 minutes ago
Inflect v2 liked a dataset about 8 hours ago
owensong/voxcpm2-synthetic-en-v1 liked a model about 8 hours ago
owensong/chatterbox-nano-ONNXOrganizations
None yet
upvoted a collection 36 minutes ago
liked a
dataset about 8 hours ago
liked a
model about 8 hours ago
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?
liked a
dataset about 13 hours ago
liked 3
models about 13 hours ago
reacted to Nymbo's post with 🚀🔥 about 13 hours ago
Post
1090
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)
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)
- 3 replies
liked a
model about 17 hours ago
liked a
Space about 17 hours ago
liked 2
models about 17 hours ago
liked a
Space 1 day ago
liked 2
models 1 day ago
updated a
bucket about 1 month ago
published a
bucket about 1 month ago
liked a
model about 1 month ago