OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano
feature-extraction model by OpenMOSS-Team
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.
This repository contains the Hugging Face remote-code implementation and weights for MOSS-Audio-Tokenizer-Nano, the lightweight audio tokenizer used by MOSS-TTS-Nano. MOSS-Audio-Tokenizer-Nano is a compact discrete audio tokenizer based on the Cat (Causal Audio Tokenizer with Transformer) architecture from MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models. The checkpoint in this repository has 21,969,664 parameters (approximately 22M), making it much smaller than the full-size MOSS-Audio-Tokenizer while preserving the 48 kHz stereo tokenizer interface used by the MOSS-TTS family. Summary: By combining a compact causal Transformer tokenizer with native 48 kHz stereo modeling, MOSS-Audio-Tokenizer-Nano reduces the deployment cost of the MOSS audio tokenizer interface while keeping high-fidelity reconstruction for speech, general audio, and music. It provides a lightweight, low-frame-rate, and streaming-friendly discrete audio representation for MOSS-TTS-Nano and other real-time speech generation workflows. This repository contains a lightweight remote-code implementation that mirrors the current Hugging Face Transformers transformers.models.mossaudiotokenizer module. Load it with trustremotecode=True…
Read the full model card ↗ · Preview checked 2026-11-01T01:46:33.417Z
Inside the original model card — Document outline
- MOSS-Audio-Tokenizer-Nano
- Key Features
- Evaluation Metrics
- Usage
- Quickstart
- Attention Backend And Compute Dtype
- Streaming
- Continuous Batch Streaming Decode
- Repository Layout
- Citation
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
OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano is a feature-extraction model repository published by OpenMOSS-Team on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- feature-extraction
- Library
- transformers
- Recent downloads (30 days)
- 182,657
- Cumulative likes
- 29
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 21,969,664
- Architecture
- MossAudioTokenizerModel
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-04-02T10:54:21.000Z
- Last modified
- 2026-04-29T07:25:23.000Z
Compatibility and lineage
Language coverage was not reported.
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 2026-11-01T06:54:29.511Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.