Tag
tiny-voca 是一个仅 4.5M 参数的轻量英文文本转语音模型,包含两个美式英语音色,在四线程 CPU 上运行速度约为实时的 70 倍,提供 PyTorch 与 ONNX 权重、代码及浏览器试用空间。
AuroraAI-Research released AuroraTTS-100K, an extremely small English text-to-speech model with only 95,638 inference parameters, trained from scratch on LJSpeech using a differentiable harmonic+noise DSP synthesizer instead of a neural vocoder, achieving UTMOS 3.53 with very fast inference.
Kyutai announces that its Pocket TTS model, which supports voice cloning, has been shrunk to just 1.9 million parameters—roughly 10x smaller than before—demonstrating that high-quality speech synthesis can run on extremely lightweight models.
AuroraASR-1M 发布:一个参数量低于 1M 的极小权重共享 Conformer-CTC 语音识别模型,在 LibriSpeech 上训练,支持 FP32/FP16/INT8 多精度,CPU 上也能实现远超实时的推理速度。
Cactus Compute releases Whistle, a 16.9 MB open speech recognition model running dependency-free on CPU across mobile, wearables, robotics, automotive and microcontrollers. It transcribes seven languages with word timestamps and speech embeddings, reaching first token in 11 ms, and shares Needle's C++ engine and quantisation.
The user praises the Ling 3.0 Tiny AI model for being fast and efficient on low-end PCs, comparing it favorably to models like Qwen 3.5 9b and Gemma 12.
Release of Ling-3.0-tiny, a hybrid reasoning model with 7.9B total parameters and only 1.3B active per token, free for a week.
A small model designed to summarize the reasoning traces of coding agents, helping improve interpretability and efficiency.
SupraLabs released SupraSafety-18M, a tiny 18M-parameter BERT-style content moderation model trained on NVIDIA's Nemotron-3.5 dataset. It achieves 81.2% accuracy and runs efficiently on edge devices.
The paper introduces VGB, a process-guided sampling algorithm with probabilistic backtracking, which significantly improves coding performance on tiny 0.5B models by being robust to verifier errors.
Inflect-Nano-v1 is a tiny English text-to-speech model with 4.63M total inference parameters, including its vocoder, designed for local, efficient speech synthesis experiments.
Built a repository to train a tiny language model (25M parameters) from scratch on 8GB VRAM, with support for MTP but noting limitations of mHC and BitNet.