SonicVerse

amaai-lab/SonicVerse

Audio Text To TextpeftLicense: apache-2.0

Tracked by OpenModelStats since August 25, 2026View on Hugging Face ↗

Downloads 30D: 32
Total downloads: 2,061
Gained 7D: +2(increase); 0.1%(up) vs baseline
Gained 30D: —
Likes: 21; +0 in 7D
Rank · tracked models: —; –this week
Parameters: —
Last source update: Jun 19, 2025

SonicVerse gained 2 downloads during the last seven tracked days.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-25. Charts appear as daily observations accumulate.

Overview

SonicVerse is a audio text to text model published by amaai-lab. OpenModelStats has tracked the model since Aug 25, 2026, most recently observing it Oct 3, 2026.

Published: Apr 22, 2025
Last updated: Jun 19, 2025
Library: peft
License: apache-2.0
Task: Audio Text To Text
Parameters: —
Spaces: 2
Derivative models: —
Velocity 7D/day: 0

peftsafetensorsmistral-lmmaudio-text-to-textendataset:amaai-lab/MusicBencharxiv:2506.15154base_model:m-a-p/MERT-v1-95Mbase_model:adapter:m-a-p/MERT-v1-95Mlicense:apache-2.0region:us

Publisher

amaai-labView publisher statistics →

Model family

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

Base model

MERT-v1-95M275.6K

Sibling models

CultureMERT-95M130

Similar models

Models similar to SonicVerse
Model	Task	DL 30D	Likes	Params
MOSS-Music-8B-Instruct-GGUFscragnog	Audio Text To Text	421.6K	2	—
Qwen2-Audio-7B-InstructQwen	Audio Text To Text	280.2K	561	8.4B
MOSS-Transcribe-DiarizeOpenMOSS-Team	Audio Text To Text	218K	462	909M
ultravox-v0_5-llama-3_2-1bfixie-ai	Audio Text To Text	132.5K	96	683M
VibeVoice-ASR-HFmicrosoft	Audio Text To Text	79.3K	182	8.3B
audio-flamingo-3-hfnvidia	Audio Text To Text	52K	196	8.3B