wav2vec2-large-robust-12-ft-emotion-msp-dim vs MERT-v1-330M

Specs, VRAM requirements and download trends — updated 2 September 2026.

audeering · A · Open weights
Params
170 M
Context
—
30d
217 K
cc-by-nc-sa-4.0 · non-commercial
m-a-p · B · Open weights
Params
—
Context
—
30d
207 K
cc-by-nc-4.0 · non-commercial

Specification comparison

Differences are highlighted; identical values are muted.

Specification wav2vec2-large-robust-12-ft-emotion-msp-dim MERT-v1-330M
Parameters 170 M —
Architecture Wav2Vec2ForSpeechClassification MERTModel
Context length — —
Licence cc-by-nc-sa-4.0 cc-by-nc-4.0
Commercial use Not allowed Not allowed
Languages 1 —
Downloads 30d 216,886 207,370
Downloads all time 16.8 M 2.5 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2022-04-06 2023-03-17

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

1.2 M207 K
wav2vec2-large-robust-12-ft-emotion-msp-dim MERT-v1-330M

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

wav2vec2-large-robust-12-ft-emotion-msp-dim · fp16 1.3 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons