midashenglm-gen

mispeech/midashenglm-gen

Text to Audio2.9B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
185
Total downloads
1,292
Gained 7D
+46(increase)
4.0%(up) vs baseline
Gained 30D
—
Likes
45
+2 in 7D
Rank · tracked models
#52,202
490(down 490 places)this week
Parameters
2.9B
Last source update
Aug 13, 2026
Momentum
58.1
  • midashenglm-gen gained 46 downloads during the last seven tracked days.
  • It moved from #86 to #87 among tracked Text to Audio models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

midashenglm-gen is a text to audio model published by mispeech. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 6, 2026.

Published
Aug 12, 2026
Last updated
Aug 13, 2026
Library
transformers
License
apache-2.0
Task
Text to Audio
Parameters
2,885,826,948
Spaces
—
Derivative models
1
Velocity 7D/day
7
transformerssafetensorsmidashenglm-genfeature-extractionaudio-generationtext-to-audioflow-matchingdashengcustom_codearxiv:2608.11804license:apache-2.0region:us

Model family

Based on base-model relationships reported by the source's metadata.

Derivative models

Similar models

Models similar to midashenglm-gen
ModelDL 30D
AudioXzhangj1an2,125
SongGeneration-v2-medium-4bitmlx-community35
SongGeneration-v2-medium-8bitmlx-community18
musicgen-stereo-melody-largefacebook318
MiniMax-Music3MiniMaxAI7,040
musicgen-stereo-largefacebook6,388
mispeech/midashenglm-gen — Downloads, Growth & Stats | OpenModelStats