{"v":1,"id":"model:hf:nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps","slug":"model-nvidia-nemo-nano-codec-22khz-1-89kbps-21-5fps","kind":"model","category":"embedding","title":"nemo-nano-codec-22khz-1.89kbps-21.5fps","summary":"The NeMo NanoCodec is a neural audio codec that leverages finite scalar quantization and adversarial training with large speech language models to achieve state-of-the-art audio compression across di…","source":{"provider":"hf","ref":"nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps","url":"https://huggingface.co/nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps","rev":"fc00890b604aa2de298d2641ffc6c5f6caf8c4d7","fetchedAt":"2026-10-02T20:52:15.286Z","etag":"W/\"779-ylZpCw4tmL+XIwUpJZtt+VHhFMI\""},"author":{"name":"nvidia","url":"https://huggingface.co/nvidia"},"license":{"spdx":null,"raw":"other","url":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":18049,"downloadsWeek":327838,"likes":20,"stars":130156,"openIssues":2528,"lastRelease":{"tag":"v0.5.0","at":"2026-09-23T20:50:06Z"},"pushedAt":"2026-10-02T20:17:08Z","takenAt":"2026-10-02T20:52:15.286Z"},"tags":["nemo","gguf","feature-extraction"],"pipeline":"feature-extraction","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-08-05T14:56:02.000Z","collectedAt":"2026-10-02T20:52:15.286Z","review":{"numbers":["18,049 downloads on Hugging Face","20 likes","license other","0.1 GB for nemo_nano_codec_22khz_1.89kbps_21.5fps.decoder.f16.gguf","130,156 stars on ggml-org/llama.cpp","2,528 open issues and PRs","last release v0.5.0 on 2026-09-23","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:52:15.286Z","http":200},"description":"# NVIDIA NeMo NanoCodec\n\nimg{\ndisplay: inline-table;\nvertical-align: small;\nmargin: 0;\npadding: 0;\n}\n\n[](#model-architecture)\n| [](#model-architecture)\n| [](#datasets)\n\nThe [NeMo NanoCodec](https://arxiv.org/abs/2508.05835v1) is a neural audio codec that leverages finite scalar quantization and adversarial training with large speech language models to  achieve state-of-the-art audio compression across different bitrate and frame rate ranges.  \nModel variant details:\n\n| Sample Rate | Frame Rate | Bit Rate   | # Codebooks | Codebook Size | Embed Dim   | FSQ Levels   |\n|:-----------:|:----------:|:----------:|:-----------:|:-------------:|:-----------:|:------------:|\n| 22050       | 21.5       | 1.89kpbs   | 8          | 2016          | 32          | [8, 7, 6, 6] |\n\nThis model is ready for commercial/non-commercial use.\n\n## NeMo NanoCodec variants\n\nModel | Sample Rate | Frame Rate | Bit Rate   | # Codebooks | Codebook Size | Embed Dim   | FSQ Levels   |\n:-----------:|:-----------:|:----------:|:----------:|:-----------:|:-------------:|:-----------:|:------------:|\n[1.78kbps-12.5fps](https://huggingface.co/nvidia/nanocodec-22khz-1.78kbps-12.5fps)| 22050       | 12.5      | 1.78kpbs   | 13          | 2016          | 52          | [8, 7, 6, 6] |\n[0.6kbps-12.5fps](https://huggingface.co/nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps) | 22050       | 12.5      | 0.6kpbs   | 4          | 4032          | 16          | [9, 8, 8, 7] |\n[1.89kbps-21.5fps](https://huggingface.co/nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps) | 22050       | 21.5       | 1.89kpbs   | 8          | 2016          | 32          | [8, 7, 6, 6] |\n\n⚠️ **Note on 0.6kbps-12.5fps**  \nThis variant is designed for **fine-tuning with a limited set of speakers**, as shown in our [S2S Duplex paper](https://www.isca-archive.org/interspeech_2025/hu25f_interspeech.html).  \nIt is **not recommended** for general-purpose audio encoding or de…\n\nSource: https://huggingface.co/nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps","install":{"kind":"model","hfId":"nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps","gated":false,"format":"gguf","files":[{"name":"nemo_nano_codec_22khz_1.89kbps_21.5fps.decoder.f16.gguf","size":78823104,"quant":"F16","sha256":"cc86d36d821a27cdc1d4ef600a3e2b0dabe76e88fcc2a8652d9543134c07ef2d"}],"totalBytes":78823104,"suggestedFile":"nemo_nano_codec_22khz_1.89kbps_21.5fps.decoder.f16.gguf","requirements":{"ramGb":1,"diskBytes":78823104,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp"],"command":"lsh models install hf:nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps"}}