mini-omni

gpt-omni/mini-omni

Text to SpeechLicense: mit
Tracked by OpenModelStats since September 24, 2026View on Hugging Face ↗
Downloads 30D
0
Total downloads
6
Gained 7D
0
Gained 30D
—
Likes
445
+0 in 7D
Rank · tracked models
#54,814
49(down 49 places)this week
Parameters
—
Last source update
Sep 4, 2024
Momentum
4.4
  • It moved from #623 to #666 among tracked Text to Speech models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

mini-omni is a text to speech model published by gpt-omni. OpenModelStats has tracked the model since Sep 24, 2026, most recently observing it Oct 1, 2026.

Published
Aug 27, 2024
Last updated
Sep 4, 2024
Library
—
License
mit
Task
Text to Speech
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
0
text-to-speechspeech-to-speechenarxiv:2408.16725base_model:Qwen/Qwen2-0.5Bbase_model:finetune:Qwen/Qwen2-0.5Blicense:mitregion:us

Publisher

gpt-omniView publisher statistics →

Derived from Qwen/Qwen2-0.5B (reported by the source; parent not yet tracked).

Similar models

Models similar to mini-omni
ModelDL 30D
Kokoro-82Mhexgrad11.5M
XTTS-v2coqui6.7M
audio.cpp-ggufaudio-cpp5.5M
Qwen3-TTS-12Hz-1.7B-CustomVoiceQwen2.4M
chatterboxResembleAI1.7M
OmniVoicek2-fsa1.4M
gpt-omni/mini-omni — Downloads, Growth & Stats | OpenModelStats