audeering / audio-classification updated 1 year ago

wav2vec2-large-robust-12-ft-emotion-msp-dim

Name: wav2vec2-large-robust-12-ft-emotion-msp-dim
Author: audeering

Please note that this model is for research purpose only. A commercial license for a model that has been trained on much more data can be acquired with audEERING. The model expects a raw audio signal as input, and outputs predictions for arousal, dominance and valence in a range of approximately 0...1. In addition, it provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2V...

Params

170 M

Context

—

Downloads 30d

751 K

Likes

173

Commercial use: not allowed · cc-by-nc-sa-4.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

751 K637 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.7 GB	1.3 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Wav2Vec2ForSpeechClassification
Parameters: 170 M
Tensor type: F32
Layers / heads: 12 / 16
Licence: cc-by-nc-sa-4.0
First seen on the Hub: 2022-04-06
Training datasets: msp-podcast
Added to our catalog: 2026-07-28

Compare with

clap-htsat-fused 6.9 M ast-finetuned-audioset-10-10-0.4593 1.2 M wav2vec2-large-xlsr-53-gender-recognition-librispeech 626 K MERT-v1-330M 560 K audiobox-aesthetics 401 K MuQ-large-msd-iter 292 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB