higurashi-ai/Haru-4B
audio-to-audio model by higurashi-ai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Code · Technical blog · Technical blog (Japanese) Haru-4B is a low-latency and multilingual full-duplex continuous spoken dialogue foundation model: it listens and speaks at the same time, the way people do on a phone call. It is a pretrained base model, released for research. and produces one frame of its own audio and text. User audio, model audio and model text are summed into a single position of the language model, so listening and speaking never wait for each other. MLP head with MeanFlow sampling produces it in one step from the language model's hidden state; there is no separate audio transformer and there are no discrete audio tokens. the voice. and Korean. The code is at : a PyTorch implementation with a web demo, an MLX implementation with a native macOS app, and a plugin for serving with vLLM-Omni. With an NVIDIA GPU (about 12 GB of memory):…
Read the full model card ↗ · Preview checked 2026-11-14T09:38:59.759Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
higurashi-ai/Haru-4B is a audio-to-audio model repository published by higurashi-ai on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- audio-to-audio
- Library
- Not reported
- Recent downloads (30 days)
- 165
- Cumulative likes
- 183
- Hugging Face trending score
- 169
- Reported safetensors parameters
- 5,270,000,897
- Architecture
- HaruForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-12T11:05:59.000Z
- Last modified
- 2026-11-13T01:22:38.000Z
Compatibility and lineage
Reported languages: en, es, pt, de, fr, zh, ja, ru, ko
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-14T06:56:53.534Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
nvidia/NVIDIA-NemotronLabs-RE-USE
aaatmy/cl1b-s6-tfilm-pinn-onnx