Fun-ASR-MLT-Nano-2512

Home/Models/FunAudioLLM/Fun-ASR-MLT-Nano-2512

FunAudioLLM/Fun-ASR-MLT-Nano-2512

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: FunAudioLLM/Fun-ASR-MLT-Nano-2512
provider: FunAudioLLM
license: apache-2.0
language: zh, en, ja, ko, vi, id, th, ms, tl, ar, hi, bg
context: —
library: funasr
vRAM (GB): —
size on disk: —
downloads: 326
likes: 58
created: —
last modified: 2026-07-22T16:28:04+00:00 (2026)
huggingface: https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512
tags: funasrspeech-recognitionasrmultilingual31-languagesend-to-endstreamingwhisper-alternativereal-timevllmautomatic-speech-recognitionzhenjakoviidthmstlarhibghr

benchmark	category	score	context	conf	evidence
WER FLEURS	speech-asr	5.78	Fleurs-en	medium	`\| Fleurs-en \| 5.78 \| 6.95 \| 6.23 \| 9.39 \| 9.39 \| 6.99 \| 3.03 \| 10.79 \| 5.96 \| 4.74 \|`
WER LibriSpeech	speech-asr	4.19	Librispeech-other	medium	`\| Librispeech-other \| 4.19 \| 4.43 \| 3.43 \| 2.84 \| 5.69 \| 2.63 \| 2.42 \| 4.52 \| 4.33 \| 3.03 \|`
WER FLEURS	speech-asr	3.65	Fleurs-zh	medium	`\| Fleurs-zh \| - \| 3.65 \| 5.18 \| 3.43 \| 3.23 \| 3.11 \| 2.68 \| 4.81 \| 2.56 \| 2.53 \|`
WER LibriSpeech	speech-asr	2.0	Librispeech-clean	medium	`\| Librispeech-clean \| 2.00 \| 2.17 \| 1.86 \| 1.58 \| 2.8 \| 1.32 \| 1.17 \| 1.84 \| 1.76 \| 1.51 \|`

none scraped.