kyutai/mimi
feature-extraction model by kyutai
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.
Mimi codec is a state-of-the-art audio neural codec, developped by Kyutai, that combines semantic and acoustic information into audio tokens running at 12.5Hz and a bitrate of 1.1kbps. Mimi is a high-fidelity audio codec leveraging neural networks. It introduces a streaming encoder-decoder architecture with quantized latent space, trained in an end-to-end fashion. It was trained on speech data, which makes it particularly adapted to train speech language models or text-to-speech systems. Use the following code to get started with the Mimi model using a dummy example from the LibriSpeech dataset (9MB). First, install the required Python packages: Then load an audio sample, and run a forward pass of the model: See the main README file. Mimi can be used directly as an audio codec for real-time compression and decompression of speech signals. It provides high-quality audio compression and efficient decoding. The model is not intended to be used to impersonate…
Read the full model card ↗ · Preview checked 2026-10-31T11:50:31.469Z
Inside the original model card — Document outline
- Model Card for Mimi
- Model Details
- Model Description
- Model Sources
- Uses
- How to Get Started with the Model
- Usage with transformers
- Usage with Moshi
- Direct Use
- Out-of-Scope Use
- Bias, Risks, and Limitations
- Training Details
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
kyutai/mimi is a feature-extraction model repository published by kyutai 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)
- 168,001
- Cumulative likes
- 341
- Hugging Face trending score
- 2
- Reported safetensors parameters
- 96,151,393
- Architecture
- MimiModel
- License
- cc-by-4.0
- Access
- Not gated by Hugging Face
- Created
- 2024-09-10T12:38:15.000Z
- Last modified
- 2025-07-02T15:23:37.000Z
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.