MMLForge Search models, datasets, tasks… Start free
Home › Models › Audio Classification › anyreach-ai/dualturn-qwen2.5-mimi-0.5B
D

anyreach-ai/dualturn-qwen2.5-mimi-0.5B

Audio Classification·anyreach-ai· 1.0K· 1
apache-2.0 Audio Classification 658.6M params

Real-time dual-channel turn-taking model. Given stereo audio (user mic + agent speaker), predicts per-frame:

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull anyreach-ai/dualturn-qwen2.5-mimi-0.5B

Model details

Task
Audio Classification
Provider
anyreach-ai
Parameters
658.6M
Size
6.1 GB
License
apache-2.0
Downloads
1.0K
Likes
1
Paper
arXiv:2603.08216
Updated
2026-04-06

About anyreach-ai/dualturn-qwen2.5-mimi-0.5B

Real-time dual-channel turn-taking model. Given stereo audio (user mic + agent speaker), predicts per-frame:

Related Audio Classification

C laion/clap-htsat-fused Audio Classification ·153.6M params 14.7M 107 🤗 HF W alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech Audio Classification ·315.7M params 587.0K 48 🤗 HF W audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim Audio Classification ·165.3M params 584.0K 171 🤗 HF A MIT/ast-finetuned-audioset-10-10-0.4593 Audio Classification ·86.6M params 529.0K 360 🤗 HF M m-a-p/MERT-v1-330M Audio Classification 466.6K 90 🤗 HF W audeering/wav2vec2-large-robust-24-ft-age-gender Audio Classification ·317.5M params 444.1K 56 🤗 HF

Browse all Audio Classification models →