handy-computer/Voxtral-Mini-4B-Realtime-2602-gguf
automatic-speech-recognition model by handy-computer
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.
GGUF conversions of mistralai/Voxtral-Mini-4B-Realtime-2602 for use with transcribe.cpp. Ported from upstream commit 2769294, pinned 2026-06-06. Validated against the Transformers reference at transcribe.cpp commit 483c122 on 2026-06-06. Streaming audio-LLM speech-to-text. A 970M causal audio encoder (left-pad causal conv stem + 32-layer sliding-window RoPE transformer) feeds a 4-frame-group projector whose audio embeddings are added onto a 3.4B Ministral decoder (26 layers, GQA 32/8, NEOX RoPE) with delay-token latency conditioning, emitting one text token per 80 ms audio slot (12.5 Hz). Takes a 16 kHz mono WAV and supports both incremental streaming (configurable latency/quality via --stream-chunk-ms and --stream-voxtral-delay) and offline transcription using an accuracy-first 2400 ms delay. Architecturally distinct from the offline Voxtral 2507 family — own arch, streaming frontend, causal encoder, additive audio fusion. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 8, timestamps none. Figures without a commit were published before provenance was recorded. Scored with the Whisper…
Read the full model card ↗ · Preview checked 2026-10-31T07:56:23.651Z
Inside the original model card — Document outline
- Voxtral-Mini-4B-Realtime-2602: transcribe.cpp GGUF
- Downloads
- Usage
- License
- Original Model Card
- Voxtral Mini 4B Realtime 2602
- Key Features
- Use Cases
- Recommended Settings
- Benchmark Results
- Fleurs
- Long-form English
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: 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
handy-computer/Voxtral-Mini-4B-Realtime-2602-gguf is a automatic-speech-recognition model repository published by handy-computer on Hugging Face. The source reports the transcribe.cpp library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- automatic-speech-recognition
- Library
- transcribe.cpp
- Recent downloads (30 days)
- 478,320
- Cumulative likes
- 9
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-06-05T13:03:56.000Z
- Last modified
- 2026-10-16T08:29:59.000Z
Compatibility and lineage
Reported languages: en, fr, es, de, ru, zh, ja, it, pt, nl, ar, hi, ko
Reported base models: mistralai/Voxtral-Mini-4B-Realtime-2602
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 2026-11-01T06:51:32.899Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
jonatasgrosman/wav2vec2-large-xlsr-53-japanese