Search public pages, research tools, and SAVRN solutions.
Open-weight model · Audio classification
by audEERING GmbH audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim
Please note that this model is for research purpose only. A commercial license for a model that has been trained on much more data can be acquired with audEERING.
What it takes to serve wav2vec2-large-robust-12-ft-emotion-msp-dim (165M 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 | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x 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, read Sep 18, 2026.
Three numbers come out of this model per clip: arousal, dominance and valence, each roughly 0 to 1. audEERING GmbH pruned the encoder from 24 to 12 layers before fine-tuning on MSP-Podcast, leaving 165M parameters. In 16-bit the weights are 0.3 GB and it runs in 0.4 GB, so the entry card, one MI300X at $1.85 per hour on-demand, is more than one instance needs; treat it as a rounding error on a busy card.
The license decides this one. CC BY-NC-SA 4.0 allows non-commercial sharing and adapting with credit, requires adaptations to carry the same license, and commercial use needs separate permission. The publisher calls the release research only and offers a commercial license for a model trained on much more data, so production use is a licensing conversation first. Check the paper, arXiv:2203.07378, and the ONNX export at doi:10.5281/zenodo.6221127 if you do not serve through transformers.
Please note that this model is for research purpose only. A commercial license for a model that has been trained on much more data can be acquired with audEERING. The model expects a raw audio signal as input, and outputs predictions for arousal, dominance and valence in a range of approximately 0...1. In addition, it provides the pooled states of the last transformer layer. The model was created by fine-tuning The model was pruned from 24 to 12 transformer layers before fine-tuning. An ONNX export of the model is available from doi:10.5281/zenodo.6221127. Further details are given in the associated paper and tutorial.
Excerpt from the card by audEERING GmbH, licensed cc-by-nc-sa-4.0.
8 files, 1.3 GB in total. The weights are 2 files totalling 1.3 GB in bin, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 661.4 MB | efa5ac1a13b2 |
| pytorch_model.bin | Weights | 661.4 MB | 176d9d1ce29a |
| config.json | Configuration | 2.3 KB | — |
| preprocessor_config.json | Configuration | 214 B | — |
| LICENSE | Documentation | 20.9 KB | — |
| README.md | Documentation | 3.9 KB | — |
| .gitattributes | Repository | 1.3 KB | — |
| vocab.json | Tokenizer | 2 B | — |
Released by audEERING GmbH through its official repository on Hugging Face.
| Precision | Weights in memory |
|---|---|
| As published | 1.3 GB |
| 16-bit | 0.3 GB |
| 8-bit | 0.2 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0.4 GB at 16-bit and 0.1 GB at 4-bit: the weights (165M parameters) plus a working margin. A long context needs more.
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.
Not without separate permission. wav2vec2-large-robust-12-ft-emotion-msp-dim 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.
LAION-CLAP was trained on LAION-audio-630k The abstract of the paper states that: You can use this model for zero shot audio classification or extracting audio and/or textual features. You can also get the audio and text embeddings using ClapModel If you are using this model for your work, please consider citing the original paper
This model has been pushed to the Hub using the PytorchModelHubMixin integration: Unified automatic quality assessment for speech, music, and sound. Paper arXiv / MetaAI. Blogpost ai.meta.com This repository requires Python 3.9 and Pytorch 2.2 or greater. To install, you can clone this repo and run: if you only want to predict aesthetic scores from certain timestamp and save it as input.jsonl If you haven't downloade the checkpoint, the script will try to download it automatically. Otherwise, you can provide the path by --ckpt /path/to/checkpoint.pt If you have SLURM, run the following command Please adjust CPU & GPU settings using --slurm-gpu, --slurm-cpu depending on your nodes. 3. Output…
Fine-tuned facebook/wav2vec2-base for audio classification of single drum/percussion sounds into 10 classes. - clap, conga, crash, cymbal, hat, kick, ride, rim, snare, tom - Trained on short, single-hit drum sounds. Performance may drop on long mixes, multiple overlapping sounds, or very different recording conditions.
This model is a fine-tuned version of facebook/wav2vec2-base-960h for Speech Emotion Recognition (SER). It has been trained using a Frozen Feature Extractor strategy to preserve the model's acoustic understanding while adapting to emotion detection. This approach ensures stable performance and prevents "Catastrophic Forgetting," achieving nearly 80% accuracy on the validation set. Update: The "Calm" and "Neutral" classes have been merged to improve classification consistency, resulting in 7 distinct emotion classes. The model was trained on a combined dataset of ~12,000 audio files from: The model classifies audio into one of the following emotions: 1. Angry 2. Disgust 3. Fear 4. Happy 5.…
Wav2Vec2: Self-Supervised Learning for Speech Recognition: https://arxiv.org/pdf/2006.11477 male female Common-Voice-Gender-Detection is designed for: Speech Analytics – Assist in analyzing speaker demographics in call centers or customer service recordings. Conversational AI Personalization – Adjust tone or dialogue based on gender detection for more personalized voice assistants. Voice Dataset Curation – Automatically tag or filter voice datasets by speaker gender for better dataset management. Research Applications – Enable linguistic and acoustic research involving gender-specific speech patterns. Multimedia Content Tagging – Automate metadata generation for gender identification in…
This model is a fine-tuned version of mo-thecreator/wav2vec2-base-finetuned on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 3e-05 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 32 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - numepochs: 5 - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2 - mo-thecreator