wav2vec2-large-robust-12-ft-emotion-msp-dim vs hubert-large-speech-emotion-recognition-russian-dusha-finetuned

Specs, VRAM requirements and download trends — updated 6 August 2026.

audeering · A
Params
170 M
Context
30d
751 K
cc-by-nc-sa-4.0 · non-commercial
xbgoose · B
Params
320 M
Context
30d
248 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification wav2vec2-large-robust-12-ft-emotion-msp-dim hubert-large-speech-emotion-recognition-russian-dusha-finetuned
Parameters 170 M 320 M
Architecture Wav2Vec2ForSpeechClassification HubertForSequenceClassification
Context length
Licence cc-by-nc-sa-4.0 apache-2.0
Commercial use Not allowed Allowed
Languages 1 1
Downloads 30d 751,189 247,910
Downloads all time 15.1 M 4.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-04-06 2023-05-28

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

751 K248 K
wav2vec2-large-robust-12-ft-emotion-msp-dim hubert-large-speech-emotion-recognition-russian-dusha-finetuned

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
hubert-large-speech-emotion-recognition-russian-dusha-finetuned · fp16 1.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons