Ir para o conteúdo
ModelListadosExterno
Browse files

Wav2vec2 Nigerian Language Identifier v3

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set: Loss: 0.1276 Accuracy: 0.9791

TipoOtherModelo basefacebook/wav2vec2-large-xlsr-53VersãoRevision 1eb24acBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
1,35 KB–1,18 GB
Modelo base
facebook/wav2vec2-large-xlsr-53
Versão
vRevision 1eb24ac
Atualizado
31 de out. de 2026
Downloads
9
Fonte
Hugging Face

Descrição da fonte

wav2vec2-nigerian-lid-v3

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1276
  • Accuracy: 0.9791

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: 0.0002
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • 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
  • lr_scheduler_warmup_steps: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
0.33451.02800.34390.9280
0.05972.05600.10340.9838
0.03233.08400.12330.9781
0.03224.011200.12090.9776
0.02545.014000.19610.9755
0.01036.016800.10630.9807
0.01167.019600.06690.9880
0.00038.022400.14460.9791
0.00269.025200.12330.9802
0.002110.028000.12760.9791

Framework versions

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

Fontes

1 fonte
Hugging FacePrimárioVersão 1eb24acb40c5d6768a7e3a87092bed5f4c61be44
huggingface.co/drrobot9/wav2vec2-nigerian-language-identifier-v3/tree/1eb24acb40c5d6768a7e3a87092bed5f4c61be44

Verificado 31 de out.

Download files

Artefatos de modelo

5 artefatos

checkpoint-1960/model.safetensors

safetensors · FP32 (unverified) · 1,18 GB · SHA-256 976dbb8f9a8f…d7f3 · Hugging Face

Download file

checkpoint-1960/scaler.pt

pt · 1,35 KB · SHA-256 5190e5a8eca4…b33e · Hugging Face

Download file

checkpoint-2800/model.safetensors

safetensors · FP32 (unverified) · 1,18 GB · SHA-256 f28bee75da03…9da0 · Hugging Face

Download file

checkpoint-2800/scaler.pt

pt · 1,35 KB · SHA-256 fd20daa55e0e…b17c · Hugging Face

Download file

model.safetensors

safetensors · 1,18 GB · SHA-256 976dbb8f9a8f…d7f3 · Hugging Face

Download file

Trechos de fonte

3 trechos

--- library_name: transformers license: apache-2.0 base_model: facebook/wav2vec2-large-xlsr-53 tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-nigerian-lid-v3 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-nigerian-lid-v3 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1276 - Accuracy: 0.9791 ## 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: 0.0002 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - 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 - lr_scheduler_warmup_steps: 0.1 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.3345 | 1.0 | 280 | 0.3439 | 0.9280 | | 0.0597 | 2.0 | 560 | 0.1034 | 0.9838 | | 0.0323 | 3.0 | 840 | 0.1233 | 0.9781 | | 0.0322 | 4.0 | 1120 | 0.1209 | 0.9776 | | 0.0254 | 5.0 | 1400 | 0.1961 | 0.9755 | | 0.0103 | 6.0 | 1680 | 0.1063 | 0.9807 | | 0.0116 | 7.0 | 1960 | 0.0669 | 0.9880 | | 0.0003 | 8.0 | 2240 | 0.1446 | 0.9791 | | 0.0026 | 9.0 | 2520 | 0.1233 | 0.9802 | | 0.0021 | 10.0 | 2800 | 0.1276 | 0.9791 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2

Source context: 9 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo drrobot9/wav2vec2-nigerian-language-identifier-v3

Source context: 7 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo drrobot9/wav2vec2-nigerian-language-identifier-v3