31M-param English TTS model phonon-31m-en trends on Hugging Face
gradium · hf · 2026-10-26
phonon-31m-en, a tiny 31M-parameter English text-to-speech model, is trending on Hugging Face. Built on Transformers with safetensors and GGUF formats, it targets streaming and on-device TTS use cases with an extremely lightweight footprint.
More from Models
- Nathan Lambert's first open models lecture: distillation, risks and the ecosystem explained — natolambert · 2026-10-26
- Claude's safety classifier blocks SS7 defense research, pushing a security dev to an abliterated GLM — l4rz · 2026-10-26
- Black Forest Labs open-sources 5.6B FLUX 3 Image Klein, +91 Elo with 38% fewer params — dl_weekly · 2026-10-26
- Gemma 4 26B-A4B runs offline on a 16 GB Mac: 33/40 on TypeScript tasks at 31 tok/s — Mission-Sir-1614 · 2026-10-26
- Sakana AI to pretrain first domestic model Sakana Sawara for defense and cybersecurity by 2027 — tkasasagi · 2026-10-26
- NVIDIA tutorial: post-training Nemotron for Europe with Persona datasets and LoRA — NVIDIA Developer · 2026-10-26