Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Wav2vec2 Large Xls R 300m Dm32

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: Loss: 0.6844 Accuracy: 0.5833

ArtOtherBasismodellfacebook/wav2vec2-xls-r-300mVersionRevision f0bf975

Modellquelle

Art
Other
Dateigröße
1,18 GB
Basismodell
facebook/wav2vec2-xls-r-300m
Version
vRevision f0bf975
Aktualisiert
13. Sept. 2026
Downloads
2
Quelle
Hugging Face

Quellenbeschreibung

wav2vec2-large-xls-r-300m-dm32

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:

  • Loss: 0.6844
  • Accuracy: 0.5833

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: 2
  • total_train_batch_size: 16
  • 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: 22
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
No log2.2759340.68060.5833
No log4.5517680.68100.5833
No log6.82761020.68620.5833
1.34579.06901360.68660.5833
1.345711.34481700.68060.5833
1.345713.62072040.68510.5833
1.340615.89662380.68950.5833
1.340618.13792720.68590.5833
1.340620.41383060.68440.5833

Framework versions

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

Quellen

1 Quelle
Hugging FacePrimärVersion f0bf975d7d682a8eafe2ab17a1067143224ba6a3
huggingface.co/cblanco5/wav2vec2-large-xls-r-300m-dm32/tree/f0bf975d7d682a8eafe2ab17a1067143224ba6a3

Verifiziert 13. Sept.

Modellartefakte

1 Artefakt

model.safetensors

safetensors · 1,18 GB · SHA-256 49178ad7e384…cdab · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

--- library_name: transformers license: apache-2.0 base_model: facebook/wav2vec2-xls-r-300m tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-large-xls-r-300m-dm32 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. --> # wav2vec2-large-xls-r-300m-dm32 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6844 - Accuracy: 0.5833 ## 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: 2 - total_train_batch_size: 16 - 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: 22 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | No log | 2.2759 | 34 | 0.6806 | 0.5833 | | No log | 4.5517 | 68 | 0.6810 | 0.5833 | | No log | 6.8276 | 102 | 0.6862 | 0.5833 | | 1.3457 | 9.0690 | 136 | 0.6866 | 0.5833 | | 1.3457 | 11.3448 | 170 | 0.6806 | 0.5833 | | 1.3457 | 13.6207 | 204 | 0.6851 | 0.5833 | | 1.3406 | 15.8966 | 238 | 0.6895 | 0.5833 | | 1.3406 | 18.1379 | 272 | 0.6859 | 0.5833 | | 1.3406 | 20.4138 | 306 | 0.6844 | 0.5833 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2

Source context: 2 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo cblanco5/wav2vec2-large-xls-r-300m-dm32