deepseek-ai/DeepSeek-V4-Flash-0731
Text Generation • 304B • Updated • 156k • • 1.86k
Unknown Entity
unknownentity
AI & ML interests
None yet
Recent Activity
liked a model about 16 hours ago
deepseek-ai/DeepSeek-V4-Flash-0731 liked a model 6 days ago
fishaudio/s2-pro liked a Space 6 days ago
owensong/Inflect-v2Organizations
None yet
liked a
model about 16 hours ago
liked a
model 6 days ago
liked a
Space 6 days ago
liked a
model 6 days ago
reacted to owensong's post with 🔥 6 days ago
Post
6779
I just released Inflect v2, pushing complete TTS below 4M parameters.
Inflect-Nano-v2 fits every learned inference component, including waveform generation, into 3.96M parameters (15.97 MB FP32), making it one of the smallest publicly available complete TTS models. Inflect-Micro-v2 stays under 10M at 9.36M parameters (37.53 MB), using the extra capacity for clearer, more natural speech.
This was not about building a toy that technically produces audio. I wanted to see how much useful TTS could actually fit at this scale.
Nano stayed surprisingly close to Micro across the reported release metrics, but if you want to hear Inflect at its best, start with Micro:
owensong/Inflect-Micro-v2
Text goes in and 24 kHz speech comes out without a second learned model. Both models have PyTorch and ONNX releases: PyTorch runs on CPU or CUDA, while the browser demo runs ONNX locally through WebGPU with a WASM fallback. The Inflect code and weights are released under Apache 2.0.
Try Nano and Micro side by side:
owensong/Inflect-v2
Some people may remember the much rougher Inflect-Nano-v1 experiment. V2 was rebuilt and retrained to address its biggest weaknesses: metallic audio, unstable timing, weak prosody, and difficulty with unseen text. Nano-v2 is smaller while sounding substantially cleaner and more stable.
In an anonymous community blind test across nine voices, Micro and Nano placed second and third by normalized preference rate. Full results, samples, limitations, and inference instructions are on the model pages.
Inflect-Nano-v2:
owensong/Inflect-Nano-v2
I built Inflect independently with a limited training budget. If you test it, give it something difficult: unusual names, numbers, abbreviations, symbols, or awkward punctuation. Send me the exact text when something breaks. If you build something with it, I would genuinely love to see it.
Inflect-Nano-v2 fits every learned inference component, including waveform generation, into 3.96M parameters (15.97 MB FP32), making it one of the smallest publicly available complete TTS models. Inflect-Micro-v2 stays under 10M at 9.36M parameters (37.53 MB), using the extra capacity for clearer, more natural speech.
This was not about building a toy that technically produces audio. I wanted to see how much useful TTS could actually fit at this scale.
Nano stayed surprisingly close to Micro across the reported release metrics, but if you want to hear Inflect at its best, start with Micro:
owensong/Inflect-Micro-v2
Text goes in and 24 kHz speech comes out without a second learned model. Both models have PyTorch and ONNX releases: PyTorch runs on CPU or CUDA, while the browser demo runs ONNX locally through WebGPU with a WASM fallback. The Inflect code and weights are released under Apache 2.0.
Try Nano and Micro side by side:
owensong/Inflect-v2
Some people may remember the much rougher Inflect-Nano-v1 experiment. V2 was rebuilt and retrained to address its biggest weaknesses: metallic audio, unstable timing, weak prosody, and difficulty with unseen text. Nano-v2 is smaller while sounding substantially cleaner and more stable.
In an anonymous community blind test across nine voices, Micro and Nano placed second and third by normalized preference rate. Full results, samples, limitations, and inference instructions are on the model pages.
Inflect-Nano-v2:
owensong/Inflect-Nano-v2
I built Inflect independently with a limited training budget. If you test it, give it something difficult: unusual names, numbers, abbreviations, symbols, or awkward punctuation. Send me the exact text when something breaks. If you build something with it, I would genuinely love to see it.
- 1 reply
liked 2
models 7 days ago
reacted to Nymbo's post with 🔥 7 days ago
Post
5442
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)
- 6 replies
liked a
model 8 days ago
upvoted 4
papers 8 days ago
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 205
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Paper • 2607.13285 • Published • 232
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Paper • 2607.19191 • Published • 307
Orca: The World is in Your Mind
Paper • 2606.30534 • Published • 473
liked a
model 12 days ago
liked a
model 25 days ago
liked 2
models about 2 months ago
liked 2
models 2 months ago
upvoted a paper 3 months ago