Fun-ASR-Nano-2512-hf

FunAudioLLM/Fun-ASR-Nano-2512-hf

Speech Recognition830M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
120.3K
Total downloads
154.6K
Gained 7D
+36.9K(increase)
57.3%(up) vs baseline
Gained 30D
—
Likes
20
+2 in 7D
Rank · tracked models
#2,143
127(up 127 places)this week
Parameters
830M
Last source update
Sep 10, 2026
Momentum
96.8
  • Fun-ASR-Nano-2512-hf gained 36.9K downloads during the last seven tracked days.
  • It moved from #147 to #145 among tracked Speech Recognition models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Fun-ASR-Nano-2512-hf is a speech recognition model published by FunAudioLLM. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 12h ago.

Published
May 24, 2026
Last updated
Sep 10, 2026
Library
transformers
License
apache-2.0
Task
Speech Recognition
Parameters
829,791,840
Spaces
—
Derivative models
—
Velocity 7D/day
5,271
transformerssafetensorsfun_asr_nanoautomatic-speech-recognitionspeech-recognitionasrend-to-endmultilingualarxiv:2509.12508zhenja

Similar models

Models similar to Fun-ASR-Nano-2512-hf
ModelDL 30D
whisper-medium-quantized.w4a16RedHatAI190
whisper-medium-quantized.w8a8RedHatAI26
whisper-th-medium-combinedbiodatlab3,717
kb-whisper-mediumKBLab2,022
canary-1b-flashnvidia4,140
CrisperWhisper2.0_turbonyralabs8,704
FunAudioLLM/Fun-ASR-Nano-2512-hf — Downloads, Growth & Stats | OpenModelStats