Qwen2-Audio_PCLM_DPO

IHP-Lab/Qwen2-Audio_PCLM_DPO

Audio Text To Text8.4B parameterstransformersLicense: other

Tracked by OpenModelStats since September 29, 2026View on Hugging Face ↗

Downloads 30D: 86
Total downloads: 3,553
Gained 7D: +10(increase); 0.3%(up) vs baseline
Gained 30D: —
Likes: 3; +0 in 7D
Rank · tracked models: #32,196; 5427(down 5427 places)this week
Parameters: 8.4B
Last source update: Jun 3, 2026

Qwen2-Audio_PCLM_DPO gained 10 downloads during the last seven tracked days.
It moved from #40 to #44 among tracked Audio Text To Text models this week.

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

Overview

Qwen2-Audio_PCLM_DPO is a audio text to text model published by IHP-Lab. OpenModelStats has tracked the model since Sep 29, 2026, most recently observing it Oct 6, 2026.

Published: Jun 3, 2026
Last updated: Jun 3, 2026
Library: transformers
License: other
Task: Audio Text To Text
Parameters: 8,447,111,685
Spaces: 0
Derivative models: —
Velocity 7D/day: 1

transformerssafetensorsqwen2_audiotext2text-generationaudiospeechaudio-llmparalinguisticpclmdpovoxparadoxaudio-text-to-text

Publisher

IHP-LabView publisher statistics →

Model family

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

Base model

Qwen2-Audio-7B-Instruct288.4K

Sibling models

Similar models

Models similar to Qwen2-Audio_PCLM_DPO
Model	Task	DL 30D	Likes	Params
Qwen2-Audio-7B-InstructQwen	Audio Text To Text	288.4K	560	8.4B
Qwen2-Audio-7BQwen	Audio Text To Text	34.8K	176	8.4B
VibeVoice-ASR-HFmicrosoft	Audio Text To Text	69K	182	8.3B
midashenglm-7b-0804-fp32mispeech	Audio Text To Text	16.2K	83	8.3B
midashenglm-7b-1021-bf16mispeech	Audio Text To Text	414	3	8.3B
audio-flamingo-3-hfnvidia	Audio Text To Text	52.2K	196	8.3B