# wav2vec2-large-robust-24-ft-age-gender by audEERING GmbH Source: https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve wav2vec2-large-robust-24-ft-age-gender (318M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.6 GB | 0.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.3 GB | 0.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [wav2vec2-large-robust-24-ft-age-gender on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender/gpus) ## 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. SAVRN Research, 2026-09-18 ## Model Card The model expects a raw audio signal as input and outputs predictions for age in a range of approximately 0...1 (0...100 years) and gender expressing the probababilty for being child, female, or male. In addition, it also provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust Timit and For this version of the model we trained all 24 transformer layers. An ONNX export of the model is available from Further details are given in the associated paper and tutorial. Excerpt from the card by audEERING GmbH, licensed cc-by-nc-sa-4.0. ## Configuration Architecture Model Layers 24 Hidden size 1,024 Feed-forward size 4,096 Attention heads 16 Vocabulary size 32 Stored precision float32 Model type wav2vec2 ## Identity and Version Repository audeering/wav2vec2-large-robust-24-ft-age-gender Publisher audEERING GmbH Task Audio classification Modality Audio Library transformers Parameters 318M parameters Languages Not stated by the source Revision bad2737f529168bc3d3fcd97edfaba9583c7d36d First published 2023-09-04 Last updated 2025-03-24 ## Files and Weights 8 files, 2.5 GB in total. The weights are 2 files totalling 2.5 GB in bin, safetensors. Weights2 files · 2.5 GB Configuration2 files · 2.6 KB Tokenizer1 file · 3 B Documentation2 files · 25.0 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 1.3 GB | 5868cc9548a1 | | pytorch_model.bin | Weights | 1.3 GB | 5c630cf42d0c | | config.json | Configuration | 2.4 KB | — | | preprocessor_config.json | Configuration | 214 B | — | | LICENSE | Documentation | 20.9 KB | — | | README.md | Documentation | 4.2 KB | — | | .gitattributes | Repository | 1.5 KB | — | | vocab.json | Tokenizer | 3 B | — | ## License and Download License cc-by-nc-sa-4.0 Access Open weights, no gate Download size 2.5 GB [Download from audEERING GmbH](https://huggingface.co/audeering/wav2vec2-large-robust-24-ft-age-gender) Released by audEERING GmbH through its official repository on Hugging Face. ## Built From - Derived from facebook/wav2vec2-large-robust - Described by [arXiv:2306.16962](https://savrn.com/papers/speech-based-age-and-gender-prediction-with-transformers) - Trained on (disclosed) agender - Trained on (disclosed) mozillacommonvoice - Trained on (disclosed) timit - Trained on (disclosed) voxceleb2 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 2.5 GB | | 16-bit | 0.6 GB | | 8-bit | 0.3 GB | | 4-bit | 0.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Compare wav2vec2-large-robust-24-ft-age-gender - [wav2vec2-large-robust-24-ft-age-gender vs wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://savrn.com/models/compare/wav2vec2-large-robust-24-ft-age-gender-vs-wav2vec2-lg-xlsr-en-speech-emotion-recognition) - [wav2vec2-large-robust-24-ft-age-gender vs wav2vec2-xlsr-53-russian-emotion-recognition](https://savrn.com/models/compare/wav2vec2-large-robust-24-ft-age-gender-vs-wav2vec2-xlsr-53-russian-emotion-recognition) - [wav2vec2-large-robust-24-ft-age-gender vs wavlm-emotion-russian-resd](https://savrn.com/models/compare/wav2vec2-large-robust-24-ft-age-gender-vs-wavlm-emotion-russian-resd) ## Questions About wav2vec2-large-robust-24-ft-age-gender ### How much GPU memory does wav2vec2-large-robust-24-ft-age-gender need? About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (318M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run wav2vec2-large-robust-24-ft-age-gender on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 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. ## Similar Models Model · Audio classification ### [wavlm-emotion-russian-resd](https://savrn.com/models/wavlm-emotion-russian-resd) [Aniemore](https://savrn.com/model-publishers/aniemore) Speech emotion recognition for Russian over seven classes: anger, disgust, enthusiasm, fear, happiness, neutral, sadness. Fine-tuned from jonatasgrosman/expw2v2truwavlms363 on Aniemore/resd. Audio resampled to 16 kHz mono, clips capped at 12 s, normalized per utterance, padding masked. UA is macro-averaged recall, WA is accuracy, F1 is macro-averaged. All three test sets went through the same harness, so the rows are comparable to each other. The RESD split matches fold 1 of EmoBox bit for bit. The top entry there is WavLM-large at WA 56.47 / UA 55.87 / F1 55.82. These numbers are higher, but the training protocol differs — EmoBox freezes the encoder and trains a probe, this is a full… Open weights mit 317M parameters transformers [View model](https://savrn.com/models/wavlm-emotion-russian-resd) Model · Audio classification ### [wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://savrn.com/models/wav2vec2-lg-xlsr-en-speech-emotion-recognition) [Enrique Hernández Calabrés](https://savrn.com/model-publishers/ehcalabres) The model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english for a Speech Emotion Recognition (SER) task. The dataset used to fine-tune the original pre-trained model is the RAVDESS dataset. This dataset provides 1440 samples of recordings from actors performing on 8 different emotions in English, which are: It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 8 - lrschedulertype: linear - numepochs: 3 - mixedprecisiontraining: Native AMP Any doubt, contact me on Twitter. - Transformers 4.8.2… Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/wav2vec2-lg-xlsr-en-speech-emotion-recognition) Model · Audio classification ### [wav2vec2-xlsr-53-russian-emotion-recognition](https://savrn.com/models/wav2vec2-xlsr-53-russian-emotion-recognition) [Aniemore](https://savrn.com/model-publishers/aniemore) Speech emotion recognition for Russian over seven classes: anger, disgust, enthusiasm, fear, happiness, neutral, sadness. Fine-tuned from jonatasgrosman/wav2vec2-large-xlsr-53-russian on Aniemore/resd. Audio resampled to 16 kHz mono, clips capped at 12 s, normalized per utterance, padding masked. UA is macro-averaged recall, WA is accuracy, F1 is macro-averaged. All three test sets went through the same harness, so the rows are comparable to each other. The RESD split matches fold 1 of EmoBox bit for bit. The top entry there is WavLM-large at WA 56.47 / UA 55.87 / F1 55.82. These numbers are higher, but the training protocol differs — EmoBox freezes the encoder and trains a probe, this is a… Open weights mit 316M parameters transformers [View model](https://savrn.com/models/wav2vec2-xlsr-53-russian-emotion-recognition) Model · Audio classification ### [SER-Odyssey-Baseline-WavLM-Multi-Attributes](https://savrn.com/models/ser-odyssey-baseline-wavlm-multi-attributes) [Ali N. Salman](https://savrn.com/model-publishers/3loi) The model was trained on MSP-Podcast for the Odyssey 2024 Emotion Recognition competition baseline This particular model is the multi-attributed based model which predict arousal, dominance and valence in a range of approximately 0...1. CCC based on Test3 and Development sets of the Odyssey Competition Open weights mit 319M parameters transformers [View model](https://savrn.com/models/ser-odyssey-baseline-wavlm-multi-attributes) Model · Audio classification ### [audio_cls_1016](https://savrn.com/models/audio-cls-1016-2) [Ryusunghwan](https://savrn.com/model-publishers/ryusunghwan) This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 32 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2 Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/audio-cls-1016-2) Model · Audio classification ### [audio_cls_1016](https://savrn.com/models/audio-cls-1016-4) [Ju ung](https://savrn.com/model-publishers/juran123) This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 32 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2 Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/audio-cls-1016-4) ## audEERING GmbH [All models and datasets](https://savrn.com/model-publishers/audeering) ## Versions - [bad2737f5291](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender/versions/bad2737f5291) · current 2026-10-23 ## Explore More - [All audio classification models](https://savrn.com/models/tasks/audio-classification) - [All models under cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Hugging Face record](https://huggingface.co/audeering/wav2vec2-large-robust-24-ft-age-gender) - [How the hub is built](https://savrn.com/model-hub/methodology)