Diamond 1.0 Speech Restoration Model Goes Open Source
bdsqlsz · x · 2026-07-17
The open-source speech restoration model Diamond 1.0 has been released, aiming to restore degraded audio to studio-quality 44.1 kHz speech.
- Trained from scratch without using any pre-trained backbone model
- Has 1.666 billion parameters and required only 63 GPU hours for training
- Ranks 2nd out of 6 models on DNSMOS
- Reportedly outperforms models trained on four times the amount of data
- Released under the Apache 2.0 license and ready for trial
More from Multimodal
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- MiniMax H3 MAX nails cooking anime clips: 15-second curry demo with prompts shared — Hailuo_AI · 2026-09-11
- MiniMax Music Production Toolkit 2.5 for ComfyUI adds full mastering chain — Vivid_Promise1700 · 2026-09-11
- New Node Finder for ComfyUI ranks fresh nodes by star velocity and recency — Luke2642 · 2026-09-11
- Using a finisher move on one mosquito with MiniMax H3 MAX — the bug survives — Hailuo_AI · 2026-09-11