Ir para o conteúdo
ModelVerificadoExterno
Baixar

Wav2vec2 Large Xls R 300m Dm32 Augmented

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: 0.6039 Accuracy: 0.7083 F1: 0.6901 Precision: 0.7176 Recall: 0.7083

Fontehuggingface.co/SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented/tree/22af68bc33fbfaf3968910d4cb397af3edb5d4ba
TipoOtherModelo basefacebook/wav2vec2-xls-r-300mVersãoRevision 22af68bPublicador@SucharithaSCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
1,18 GB
Modelo base
facebook/wav2vec2-xls-r-300m
Versão
vRevision 22af68b
Atualizado
2 de out. de 2026
Publicador
@SucharithaS
Downloads
6
Parâmetros
300M
Tarefas
Vídeo para vídeo
Fonte
Hugging Face

Descrição da fonte

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

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: 0.6039
  • Accuracy: 0.7083
  • F1: 0.6901
  • Precision: 0.7176
  • Recall: 0.7083

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: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 25
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracyF1PrecisionRecall
No log2.39340.69770.45830.42740.51390.4583
No log4.77680.69000.58330.42980.34030.5833
0.69257.161020.67950.58330.42980.34030.5833
0.69259.541360.68390.58330.42980.34030.5833
0.692511.931700.69210.6250.6250.6250.625
0.690214.322040.67990.60420.47520.76420.6042
0.690216.72380.67520.58330.42980.34030.5833
0.690219.092720.63520.70830.70830.70830.7083
0.671721.473060.64920.70830.69010.71760.7083
0.671723.863400.60390.70830.69010.71760.7083

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.10.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.15.2

Fontes

1 fonte
Hugging FacePrimárioVersão 22af68bc33fbfaf3968910d4cb397af3edb5d4ba
huggingface.co/SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented/tree/22af68bc33fbfaf3968910d4cb397af3edb5d4ba

Verificado 2 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 1,18 GB · SHA-256 32133b83171c…a5ea · Hugging Face

Baixar

Trechos de fonte

3 trechos
Readme11 de jul.huggingface.co/SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented

--- license: apache-2.0 base_model: facebook/wav2vec2-xls-r-300m tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: wav2vec2-large-xls-r-300m-dm32-augmented 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-augmented 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: 0.6039 - Accuracy: 0.7083 - F1: 0.6901 - Precision: 0.7176 - Recall: 0.7083 ## 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: 3e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 200 - num_epochs: 25 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | No log | 2.39 | 34 | 0.6977 | 0.4583 | 0.4274 | 0.5139 | 0.4583 | | No log | 4.77 | 68 | 0.6900 | 0.5833 | 0.4298 | 0.3403 | 0.5833 | | 0.6925 | 7.16 | 102 | 0.6795 | 0.5833 | 0.4298 | 0.3403 | 0.5833 | | 0.6925 | 9.54 | 136 | 0.6839 | 0.5833 | 0.4298 | 0.3403 | 0.5833 | | 0.6925 | 11.93 | 170 | 0.6921 | 0.625 | 0.625 | 0.625 | 0.625 | | 0.6902 | 14.32 | 204 | 0.6799 | 0.6042 | 0.4752 | 0.7642 | 0.6042 | | 0.6902 | 16.7 | 238 | 0.6752 | 0.5833 | 0.4298 | 0.3403 | 0.5833 | | 0.6902 | 19.09 | 272 | 0.6352 | 0.7083 | 0.7083 | 0.7083 | 0.7083 | | 0.6717 | 21.47 | 306 | 0.6492 | 0.7083 | 0.6901 | 0.7176 | 0.7083 | | 0.6717 | 23.86 | 340 | 0.6039 | 0.7083 | 0.6901 | 0.7176 | 0.7083 | ### Framework versions - Transformers 4.37.2 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.15.2

Note2 de out.huggingface.co/SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented

Source context: 6 downloads · 0 likes · Repo SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented

Note11 de jul.huggingface.co/SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented

Source context: 2 downloads · 0 likes · Repo SucharithaS/wav2vec2-large-xls-r-300m-dm32-augmented