SAVRN Model Hub · Comparisons
hubert-large-speech-emotion-recognition-russian-dusha-finetuned vs wav2vec2-large-robust-24-ft-age-gender
Hubert-large-speech-emotion-recognition-russian-dusha-finetuned has 316M parameters and wav2vec2-large-robust-24-ft-age-gender has 318M parameters; hubert-large-speech-emotion-recognition-russian-dusha-finetuned is released under Apache License 2.0 and wav2vec2-large-robust-24-ft-age-gender under Creative Commons Attribution-NonCommercial-ShareAlike 4.0; at 16-bit, hubert-large-speech-emotion-recognition-russian-dusha-finetuned needs about 0.8 GB (1x MI300X from $1.85 an hour) and wav2vec2-large-robust-24-ft-age-gender about 0.8 GB (1x MI300X from $1.85 an hour).
| Field | hubert-large-speech-emotion-recognition-russian-dusha-finetuned xbgoose/hubert-large-speech-emotion-recognition-russian-dusha-finetuned | wav2vec2-large-robust-24-ft-age-gender audeering/wav2vec2-large-robust-24-ft-age-gender |
|---|---|---|
| Publisher | Phil | audEERING GmbH |
| Task | Audio classification | Audio classification |
| Modality | Audio | Audio |
| Parameters, as reported | 316M parameters | 318M parameters |
| Architecture | HubertForSequenceClassification | Model |
| Library | transformers | transformers |
| Context length | Not stated | Not stated |
| Repository size | 2.5 GB | 2.5 GB |
| Artifact formats | safetensors, pytorch | safetensors, pytorch |
| License | apache-2.0 | cc-by-nc-sa-4.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.8 GB | 0.8 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.2 GB | 0.2 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 2eaa20433d7e | bad2737f5291 |
| Downloads reported by the hub | 218.3k | 2.5M |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
Questions
Which is larger, hubert-large-speech-emotion-recognition-russian-dusha-finetuned or wav2vec2-large-robust-24-ft-age-gender?
wav2vec2-large-robust-24-ft-age-gender (318M parameters) is larger than hubert-large-speech-emotion-recognition-russian-dusha-finetuned (316M parameters), by the parameter counts their publishers report.
Which is cheaper to run, hubert-large-speech-emotion-recognition-russian-dusha-finetuned or wav2vec2-large-robust-24-ft-age-gender?
At 4-bit, hubert-large-speech-emotion-recognition-russian-dusha-finetuned fits on 1x MI300X from $1.85 an hour and wav2vec2-large-robust-24-ft-age-gender on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use hubert-large-speech-emotion-recognition-russian-dusha-finetuned commercially?
Yes. hubert-large-speech-emotion-recognition-russian-dusha-finetuned is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use wav2vec2-large-robust-24-ft-age-gender commercially?
Not without separate permission. wav2vec2-large-robust-24-ft-age-gender is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0. CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission.