SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

wav2vec2-large-robust-24-ft-age-gender vs wavlm-emotion-russian-resd

Wav2vec2-large-robust-24-ft-age-gender has 318M parameters and wavlm-emotion-russian-resd has 317M parameters; wav2vec2-large-robust-24-ft-age-gender is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 and wavlm-emotion-russian-resd under MIT License; at 16-bit, wav2vec2-large-robust-24-ft-age-gender needs about 0.8 GB (1x MI300X from $1.85 an hour) and wavlm-emotion-russian-resd about 0.8 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field wav2vec2-large-robust-24-ft-age-gender
audeering/wav2vec2-large-robust-24-ft-age-gender
wavlm-emotion-russian-resd
Aniemore/wavlm-emotion-russian-resd
Publisher audEERING GmbH Aniemore
Task Audio classification Audio classification
Modality Audio Audio
Parameters, as reported 318M parameters 317M parameters
Architecture Model WavLMForSequenceClassification
Library transformers transformers
Context length Not stated Not stated
Repository size 2.5 GB 2.5 GB
Artifact formats safetensors, pytorch safetensors, pytorch
License cc-by-nc-sa-4.0 mit
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 bad2737f5291 7a4ca18b34ad
Downloads reported by the hub 2.5M 23.2k
Last observed 2026-09-21 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.

Other Reported Results

These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.

wavlm-emotion-russian-resd

BenchmarkConditionsResultReported byRevisionDate
CAMEO test Task Speech Emotion RecognitionMetric AccuracyComparison conditions not established 0.2585 Aniemore
Publisher reported
Evaluated revision not stated
CAMEO test Task Speech Emotion RecognitionMetric Macro F1Comparison conditions not established 0.2104 Aniemore
Publisher reported
Evaluated revision not stated
CAMEO test Task Speech Emotion RecognitionMetric Unweighted accuracyComparison conditions not established 0.2283 Aniemore
Publisher reported
Evaluated revision not stated
Dusha podcast test Task Speech Emotion RecognitionMetric AccuracyComparison conditions not established 0.1043 Aniemore
Publisher reported
Evaluated revision not stated
Dusha podcast test Task Speech Emotion RecognitionMetric Macro F1Comparison conditions not established 0.1116 Aniemore
Publisher reported
Evaluated revision not stated
Dusha podcast test Task Speech Emotion RecognitionMetric Unweighted accuracyComparison conditions not established 0.3259 Aniemore
Publisher reported
Evaluated revision not stated
RESD test Task Speech Emotion RecognitionMetric AccuracyComparison conditions not established 0.8071 Aniemore
Publisher reported
Evaluated revision not stated
RESD test Task Speech Emotion RecognitionMetric Macro F1Comparison conditions not established 0.8026 Aniemore
Publisher reported
Evaluated revision not stated
RESD test Task Speech Emotion RecognitionMetric Unweighted accuracyComparison conditions not established 0.8058 Aniemore
Publisher reported
Evaluated revision not stated

SAVRN's Notes on wav2vec2-large-robust-24-ft-age-gender

This audEERING model estimates a speaker's age and whether the voice is a child, female or male, from raw audio. It is a 24-layer wav2vec2 at 318M parameters and draws about 2.5 million downloads a month.

The license is CC-BY-NC-SA-4.0, which rules out commercial use. Inferring age and gender from voice also raises privacy and fairness questions. Use it for research and aggregate analysis only; audEERING sells commercial licenses for its models.

Questions

Which is larger, wav2vec2-large-robust-24-ft-age-gender or wavlm-emotion-russian-resd?

wav2vec2-large-robust-24-ft-age-gender (318M parameters) is larger than wavlm-emotion-russian-resd (317M parameters), by the parameter counts their publishers report.

Which is cheaper to run, wav2vec2-large-robust-24-ft-age-gender or wavlm-emotion-russian-resd?

At 4-bit, wav2vec2-large-robust-24-ft-age-gender fits on 1x MI300X from $1.85 an hour and wavlm-emotion-russian-resd on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

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.

Can I use wavlm-emotion-russian-resd commercially?

Yes. wavlm-emotion-russian-resd is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Related Comparisons