This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
audio_cls is an open-weight model for audio classification from Jaehyeong. It has 95M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset.
Parameters95M
Context—
Weights378.3 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve audio_cls (95M 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 | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 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 Oct 18, 2026.
audio_cls on every accelerator the SAVRN Index prices, at every precision
Model Card
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
Excerpt from the card by Jaehyeong.
Configuration
- Architecture
- Wav2Vec2ForSequenceClassification
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 56
- Model type
- wav2vec2
Identity and Version
- Repository
- rnlduqwb/audio_cls
- Publisher
- Jaehyeong
- Task
- Audio classification
- Modality
- Audio
- Library
- transformers
- Parameters
- 95M parameters
- Languages
- Not stated by the source
- Revision
- 626fa95386b864494ab7a7dc16a0d37782e20f86
- First published
- 2026-10-12
- Last updated
- 2026-10-12
Files and Weights
6 files, 378.3 MB in total. The weights are 2 files totalling 378.3 MB in bin, safetensors.
Weights2 files · 378.3 MB
Configuration2 files · 3.3 KB
Documentation1 file · 2.1 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 378.3 MB | 528729dcba1d |
| training_args.bin | Weights | 5.2 KB | debebe6b4f7e |
| config.json | Configuration | 3.0 KB | — |
| preprocessor_config.json | Configuration | 212 B | — |
| README.md | Documentation | 2.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 378.3 MB
Download from Jaehyeong
Released by Jaehyeong through its official repository on Hugging Face.
Built From
- Derived from Kkonjeong/wav2vec2-base-korean
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 378.3 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About audio_cls
How much GPU memory does audio_cls need?
About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (95M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run audio_cls 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.
Similar Models
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: - evalloss: 2.6565 - evalaccuracy: 0.0756 - evalruntime: 13.3085 - evalsamplespersecond: 8.942 - evalstepspersecond: 2.254 The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2