Voxtral-Mini-4B-Realtime-2602

Home/Models/suleimanelkhoury/Voxtral-Mini-4B-Realtime-2602

suleimanelkhoury/Voxtral-Mini-4B-Realtime-2602

kind: bnb-4bit
quant: 4bit
family: misc
modality: automatic-speech-recognition
root model: mistralai/Ministral-3-3B-Base-2512
provider: suleimanelkhoury
license: apache-2.0
language: en, fr, es, de, ru, zh, ja, it, pt, nl, ar, hi
context: —
library: vllm
vRAM (GB): —
size on disk: —
downloads: 258
likes: 0
created: —
last modified: 2026-05-27T07:25:29+00:00 (2026)
huggingface: https://huggingface.co/suleimanelkhoury/Voxtral-Mini-4B-Realtime-2602
tags: vllmsafetensorsvoxtral_realtimemistral-commonautomatic-speech-recognitionenfresderuzhjaitptnlarhikoarxiv:2602.11298base_model:mistralai/Ministral-3-3B-Base-2512base_model:quantized:mistralai/Ministral-3-3B-Base-2512license:apache-2.04-bitbitsandbytes

benchmark	category	score	context	conf	evidence
WER AMI	speech-asr	14.43	GigaSpeech 2k Subset \| GISpeech 2k Subset	low	`\| Voxtral Mini Transcribe 2.0 \| Offline \| 10.39% \| 6.81% \| 14.43% \| 11.54% \| 10.42% \| 1.74% \|`
WER Switchboard	speech-asr	11.54	GigaSpeech 2k Subset \| GISpeech 2k Subset	low	`\| Voxtral Mini Transcribe 2.0 \| Offline \| 10.39% \| 6.81% \| 14.43% \| 11.54% \| 10.42% \| 1.74% \|`
WER GigaSpeech	speech-asr	6.81	GigaSpeech 2k Subset \| GISpeech 2k Subset	low	`\| Voxtral Mini Transcribe 2.0 \| Offline \| 10.39% \| 6.81% \| 14.43% \| 11.54% \| 10.42% \| 1.74% \|`
WER TED-LIUM	speech-asr	2.86		low	`\| Voxtral Mini Transcribe 2.0 \| Offline \| 4.08% \| 9.81% \| 11.69% \| 2.86% \|`

none scraped.