# wav2vec2-large-xlsr-deepfake-audio-classification by Gustavo dos Source: https://savrn.com/models/wav2vec2-large-xlsr-deepfake-audio-classification Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve wav2vec2-large-xlsr-deepfake-audio-classification (316M 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-xlsr-deepfake-audio-classification on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/wav2vec2-large-xlsr-deepfake-audio-classification/gpus) ## Model Card By Gustavo dos Reis, published under apache-2.0, revision f7050b586236. This model is a fine tuning for the deepfake audio classification task. It achieves the following results on its evalutation data: It achieves the following results on ASVspoof2019 evaluation subset Read Gustavo dos Reis's full model card This model is a fine tuning for the deepfake audio classification task. It achieves the following results on its evalutation data: - F1: 0.95 - Loss: 0.4056 It achieves the following results on [ASVspoof2019](https://www.kaggle.com/datasets/awsaf49/asvpoof-2019-dataset) evaluation subset: - Accuracy:0.9286 - Precision:0.9999 - Recall:0.9205 - F1-Score:0.9363 - Equal Error Rate (EER): 0.0401 ## Configuration Architecture Wav2Vec2ForSequenceClassification 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 Gustking/wav2vec2-large-xlsr-deepfake-audio-classification Publisher Gustavo dos Reis Task Audio classification Modality Audio Library transformers Parameters 316M parameters Languages Not stated by the source Revision f7050b586236dc910d1157f430def2d0647b02b4 First published 2024-05-15 Last updated 2024-05-15 ## Files and Weights 6 files, 1.3 GB in total. The weights are 2 files totalling 1.3 GB in bin, safetensors. Weights2 files · 1.3 GB Configuration2 files · 2.6 KB Documentation1 file · 544 B Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 1.3 GB | 8bff7244579a | | training_args.bin | Weights | 5.6 KB | 497034268dbb | | config.json | Configuration | 2.3 KB | — | | preprocessor_config.json | Configuration | 212 B | — | | README.md | Documentation | 544 B | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 1.3 GB [Download from Gustavo dos Reis](https://huggingface.co/Gustking/wav2vec2-large-xlsr-deepfake-audio-classification) Released by Gustavo dos Reis through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech](https://savrn.com/models/wav2vec2-large-xlsr-53-gender-recognition-librispeech) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.3 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. ## Built on This Model - Derived from[wav2vec2-deepfake-voice-detector](https://savrn.com/models/wav2vec2-deepfake-voice-detector) ## Questions About wav2vec2-large-xlsr-deepfake-audio-classification ### How much GPU memory does wav2vec2-large-xlsr-deepfake-audio-classification need? About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (316M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run wav2vec2-large-xlsr-deepfake-audio-classification 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-xlsr-deepfake-audio-classification commercially? Yes. wav2vec2-large-xlsr-deepfake-audio-classification 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. ## Similar Models Model · Audio classification ### [wav2vec2-large-xlsr-53-gender-recognition-librispeech](https://savrn.com/models/wav2vec2-large-xlsr-53-gender-recognition-librispeech) [Alef Iury Siqueira Ferreira](https://savrn.com/model-publishers/alefiury) This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on Librispeech-clean-100 for gender recognition. It achieves the following results on the evaluation set: The Librispeech-clean-100 dataset was used to train the model, with 70% of the data used for training, 10% for validation, and 20% for testing. The following hyperparameters were used during training: - learningrate: 3e-05 - trainbatchsize: 4 - evalbatchsize: 4 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - numepochs: 1 - mixedprecisiontraining: Native AMP - Transformers 4.28.0 - Pytorch 2.0.0+cu118 - Tokenizers 0.13.3 Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/wav2vec2-large-xlsr-53-gender-recognition-librispeech) Model · Audio classification ### [wav2vec-vm-finetune](https://savrn.com/models/wav2vec-vm-finetune) [Jake Downie](https://savrn.com/model-publishers/jakebland) This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m for voicemail detection. It is trained on a dataset of call recordings to distinguish between voicemail greetings and live human responses. This model builds on wav2vec2-xls-r-300m, a self-supervised speech model trained on large-scale multilingual data. We fine-tuned it on the first two seconds of a call. - Automated voicemail detection in AI-powered call assistants. - Filtering voicemail responses in customer service and sales call automation. - Only trianed on the English language. - Assumes the voicemail track is isolated and contains no audio from the caller. - Designed for the first two seconds of audio when calling a… Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/wav2vec-vm-finetune) Model · Audio classification ### [wav2vec2-deepfake-voice-detector](https://savrn.com/models/wav2vec2-deepfake-voice-detector) [Gary Stafford](https://savrn.com/model-publishers/garystafford) Fine-tuned Wav2Vec2 model for detecting AI-generated speech. Determines if audio was spoken by a human or created by AI text-to-speech/voice cloning software. Fine-tuned Wav2Vec2 transformer for binary audio classification (real vs AI-generated speech). Trained to distinguish authentic human speech from synthetic audio generated by AI text-to-speech and voice cloning services including: Note: This model uses transfer learning from a base model already trained for deepfake detection. Fast convergence is expected due to task similarity and TTS engine overlap with the base model's training data. The model outputs logits (raw, unnormalized scores) for two classes: Apply softmax to convert raw… Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/wav2vec2-deepfake-voice-detector) Model · Audio classification ### [hubert-large-speech-emotion-recognition-russian-dusha-finetuned](https://savrn.com/models/hubert-large-speech-emotion-recognition-russian-dusha-finetuned) [Phil](https://savrn.com/model-publishers/xbgoose) The pre-trained model is this one - facebook/hubert-large-ls960-ft The DUSHA dataset used can be found here Fine-tuned in Google Colab using Pro account with A100 GPU Freezed all layers exept projector, classifier and all 24 HubertEncoderLayerStableLayerNorm layers Used half of the train dataset - 2 epochs - train batch size = 8 - eval batch size = 8 - gradient accumulation steps = 4 - learning rate = 5e-5 without warm up and decay Achieved - accuracy = 0.86 - balanced = 0.76 - macro f1 score = 0.81 on test set, improving accucary and f1 score compared to dataset baseline Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/hubert-large-speech-emotion-recognition-russian-dusha-finetuned) 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) ## Gustavo dos Reis [All models and datasets](https://savrn.com/model-publishers/gustking) ## Versions - [f7050b586236](https://savrn.com/models/wav2vec2-large-xlsr-deepfake-audio-classification/versions/f7050b586236) · current 2026-09-18 ## Explore More - [All audio classification models](https://savrn.com/models/tasks/audio-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [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 2026-10-21. - [Hugging Face record](https://huggingface.co/Gustking/wav2vec2-large-xlsr-deepfake-audio-classification) - [How the hub is built](https://savrn.com/model-hub/methodology)