Aller au contenu
ModelPrésentéExterne
Télécharger

Audio Cls Sjs

This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: Loss: 1.2026 Accuracy: 0.7311

Sourcehuggingface.co/seohyeon122333/audio_cls_sjs/tree/def3ba79ce9f240bf63280cf746a09b3249b4a64
TypeOtherModèle de baseKkonjeong/wav2vec2-base-koreanVersionRevision def3ba7CClasse

Source du modèle

Type
Other
Taille du fichier
361 MB
Modèle de base
Kkonjeong/wav2vec2-base-korean
Version
vRevision def3ba7
Mis à jour
26 sept. 2026
Téléchargements
4
Source
Hugging Face

Description de la source

audio_cls_sjs

This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2026
  • Accuracy: 0.7311

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
No log1.0152.63190.1008
No log2.0302.46860.2101
No log3.0452.23630.3361
No log4.0602.02020.4286
No log5.0751.70580.5714
No log6.0901.52030.6303
No log7.01051.40010.6471
No log8.01201.28370.6975
No log9.01351.22770.7227
No log10.01501.20260.7311

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrincipalVersion def3ba79ce9f240bf63280cf746a09b3249b4a64
huggingface.co/seohyeon122333/audio_cls_sjs/tree/def3ba79ce9f240bf63280cf746a09b3249b4a64

Vérifié 29 août

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 361 MB · SHA-256 a360679d28b2…969e · Hugging Face

Download file

Extraits de sources

2 extraits
Readme29 aoûthuggingface.co/seohyeon122333/audio_cls_sjs

--- library_name: transformers language: - ko base_model: Kkonjeong/wav2vec2-base-korean tags: - audio-classification - minds14 - korean - generated_from_trainer metrics: - accuracy model-index: - name: audio_cls_sjs results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # audio_cls_sjs This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 1.2026 - Accuracy: 0.7311 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 15 | 2.6319 | 0.1008 | | No log | 2.0 | 30 | 2.4686 | 0.2101 | | No log | 3.0 | 45 | 2.2363 | 0.3361 | | No log | 4.0 | 60 | 2.0202 | 0.4286 | | No log | 5.0 | 75 | 1.7058 | 0.5714 | | No log | 6.0 | 90 | 1.5203 | 0.6303 | | No log | 7.0 | 105 | 1.4001 | 0.6471 | | No log | 8.0 | 120 | 1.2837 | 0.6975 | | No log | 9.0 | 135 | 1.2277 | 0.7227 | | No log | 10.0 | 150 | 1.2026 | 0.7311 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2

Note29 aoûthuggingface.co/seohyeon122333/audio_cls_sjs

Source context: 4 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo seohyeon122333/audio_cls_sjs