midashenglm-7b-0804-bf16

mispeech/midashenglm-7b-0804-bf16

Audio Text To Text8.3B parametersLicense: apache-2.0
Tracked by OpenModelStats since November 19, 2026View on Hugging Face ↗
Downloads 30D
1,685
Total downloads
4,127
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
8.3B
Last source update
Mar 17, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-11-19. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-11-19. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-11-19. Charts appear as daily observations accumulate.

Overview

midashenglm-7b-0804-bf16 is a audio text to text model published by mispeech. OpenModelStats has tracked the model since Nov 19, 2026, most recently observing it 4h ago.

Published
Sep 1, 2025
Last updated
Mar 17, 2026
Library
—
License
apache-2.0
Task
Audio Text To Text
Parameters
8,281,739,904
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsmidashenglmmultimodalaudio-language-modelaudioaudio-text-to-textcustom_codeenzhthidvi

Publisher

mispeechView publisher statistics →

Derived from Qwen/Qwen2.5-Omni-7B (reported by the source; parent not yet tracked).

Similar models

Models similar to midashenglm-7b-0804-bf16
ModelDL 30D
midashenglm-7b-0804-fp32mispeech6,123
midashenglm-7b-1021-bf16mispeech1,931
music-flamingo-hfnvidia96.9K
audio-flamingo-3-hfnvidia80.6K
music-flamingo-2601-hfnvidia5,374
audio-flamingo-next-hfnvidia4,629