MiniT2I/MiniT2I
Text-to-Image • Updated • 331 • 13
Carlo Moro PRO
cnmoro
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
MiniT2I/MiniT2I liked a model 6 days ago
owensong/Inflect-Nano-v1Organizations
liked a
model 1 day ago
reacted to owensong's post with 🔥 5 days ago
Post
6364
I just released Inflect-Nano-v1, an ultra-small 4.63 parameter text-to-speech model.
The main idea is simple: instead of only making the acoustic model tiny and relying on a larger external vocoder, Inflect-Nano-v1 keeps the complete text-to-waveform stack under 5M parameters.
Quick facts:
- 4.63M total inference parameters
- 3.46M acoustic model
- 1.17M vocoder
- 24 kHz audio
- English-only
- Single male voice
- Runs locally with a simple PyTorch inference script
Why I made it:
Most modern TTS models are much larger, and even many “small TTS” projects depend on a separate vocoder. I wanted to see how far a complete tiny TTS stack could be pushed while still producing usable speech.
It is not SOTA, and I am not trying to claim it competes with large TTS systems. The interesting part is the size-to-functionality ratio.
What works:
It can generate arbitrary English speech locally, and the model is small enough to be interesting for:
- local voice assistants
- embedded/edge experiments
- browser or WASM-style TTS exploration
- efficient inference research
- tiny-model baselines
Limitations:
The quality is still limited. It can sound robotic, stumble on difficult unseen text, and the vocoder is still a clear bottleneck. Long or unusual prompts are less reliable.
So I would frame this as a research/demo release, not a production TTS engine.
I’d love feedback from people interested in:
- tiny speech models
- vocoders
- local TTS
- efficient inference
- embedded speech synthesis
- improving small-model generalization
If people find it useful, I’m interested in putting more training budget into a stronger v2.
Model page:
owensong/Inflect-Nano-v1
The main idea is simple: instead of only making the acoustic model tiny and relying on a larger external vocoder, Inflect-Nano-v1 keeps the complete text-to-waveform stack under 5M parameters.
Quick facts:
- 4.63M total inference parameters
- 3.46M acoustic model
- 1.17M vocoder
- 24 kHz audio
- English-only
- Single male voice
- Runs locally with a simple PyTorch inference script
Why I made it:
Most modern TTS models are much larger, and even many “small TTS” projects depend on a separate vocoder. I wanted to see how far a complete tiny TTS stack could be pushed while still producing usable speech.
It is not SOTA, and I am not trying to claim it competes with large TTS systems. The interesting part is the size-to-functionality ratio.
What works:
It can generate arbitrary English speech locally, and the model is small enough to be interesting for:
- local voice assistants
- embedded/edge experiments
- browser or WASM-style TTS exploration
- efficient inference research
- tiny-model baselines
Limitations:
The quality is still limited. It can sound robotic, stumble on difficult unseen text, and the vocoder is still a clear bottleneck. Long or unusual prompts are less reliable.
So I would frame this as a research/demo release, not a production TTS engine.
I’d love feedback from people interested in:
- tiny speech models
- vocoders
- local TTS
- efficient inference
- embedded speech synthesis
- improving small-model generalization
If people find it useful, I’m interested in putting more training budget into a stronger v2.
Model page:
owensong/Inflect-Nano-v1
liked a
model 6 days ago
liked a
model 8 days ago
updated a
model 9 days ago
published a
model 9 days ago
liked a
model 10 days ago
liked a
model 12 days ago
liked a
model 13 days ago
reacted to RiverRider's post with 🧠 13 days ago
Post
3620
This is not a pipe.
Everyone is born a semiotician, no one is born knowing it. Go easy on yourself (and me) for not understanding this yet.
Computational semiotics is now an empirical study.
LLMs are not proto-minds. They are verifiably semiotic infrastructure.
This repository (or attached demo) can show you, in real time, how any frozen model (Qwen for demo) arrives at any answer by reading its latent states directly during generation.
Any questions?
RiverRider/srt-introspect
Repo:
https://github.com/space-bacon/SRT
Grok insist my intro is condescending … This is certainly true, as is the statement in my condescended opinion. I expect heat for it, let’s think this through?
Everyone is born a semiotician, no one is born knowing it. Go easy on yourself (and me) for not understanding this yet.
Computational semiotics is now an empirical study.
LLMs are not proto-minds. They are verifiably semiotic infrastructure.
This repository (or attached demo) can show you, in real time, how any frozen model (Qwen for demo) arrives at any answer by reading its latent states directly during generation.
Any questions?
RiverRider/srt-introspect
Repo:
https://github.com/space-bacon/SRT
Grok insist my intro is condescending … This is certainly true, as is the statement in my condescended opinion. I expect heat for it, let’s think this through?
liked a
Space 13 days ago
upvoted a collection 15 days ago
liked a
model 16 days ago
reacted to AxionLab-official's post with 👀 17 days ago
Post
10923
THIS IS CRAZY! THE MODEL ON THE IMAGE(Supra-50M-Reasoning) answered correctly and its QUANTIZED IN 2BIT! THE RESPONSE IS CORRECT, IN A 15MB SIZE FILE!
- 14 replies
updated a
model 19 days ago
published a
model 19 days ago
updated a
model 19 days ago
published a
model 19 days ago
liked a
model 19 days ago
liked a
model 21 days ago
