Saltar al contenido
ModelPublicadoExterno
Browse files

Wav2vec2 Nigerian Language Identifier v5

This model is a fine-tuned version of drrobot9/wav2vec2-nigerian-language-identifier-v4 on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0623 Accuracy: 0.9901

TipoOtherModelo basedrrobot9/wav2vec2-nigerian-language-identifier-v4VersiónRevision 3806647Bcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
1,35 KB–1,18 GB
Modelo base
drrobot9/wav2vec2-nigerian-language-identifier-v4
Versión
vRevision 3806647
Actualizado
31 oct 2026
Descargas
12
Fuente
Hugging Face

Descripción de la fuente

wav2vec2-nigerian-lid-v4

This model is a fine-tuned version of drrobot9/wav2vec2-nigerian-language-identifier-v4 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0623
  • Accuracy: 0.9901

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: 5e-05
  • 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: 100
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
0.00051.02190.09780.9820
0.00032.04380.05400.9892
0.00253.06570.07360.9860
0.00004.08760.05030.9919
0.00035.010950.06230.9901

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Fuentes

1 fuente
Hugging FacePrincipalVersión 3806647c03eb72472417a9537e51e726770ed287
huggingface.co/drrobot9/wav2vec2-nigerian-language-identifier-v5/tree/3806647c03eb72472417a9537e51e726770ed287

Verificado 31 oct

Download files

Artefactos del modelo

5 artefactos

checkpoint-1095/model.safetensors

safetensors · FP32 (unverified) · 1,18 GB · SHA-256 d43f8ba1fde0…ab08 · Hugging Face

Download file

checkpoint-1095/scaler.pt

pt · 1,35 KB · SHA-256 f6a2e693e046…5506 · Hugging Face

Download file

checkpoint-876/model.safetensors

safetensors · FP32 (unverified) · 1,18 GB · SHA-256 ef82aadb1d47…e928 · Hugging Face

Download file

checkpoint-876/scaler.pt

pt · 1,35 KB · SHA-256 ed60ccd84445…e93a · Hugging Face

Download file

model.safetensors

safetensors · 1,18 GB · SHA-256 ef82aadb1d47…e928 · Hugging Face

Download file

Extractos de fuentes

3 extractos

--- library_name: transformers license: apache-2.0 base_model: drrobot9/wav2vec2-nigerian-language-identifier-v4 tags: - generated_from_trainer metrics: - accuracy model-index: - name: wav2vec2-nigerian-lid-v4 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-v4 This model is a fine-tuned version of [drrobot9/wav2vec2-nigerian-language-identifier-v4](https://huggingface.co/drrobot9/wav2vec2-nigerian-language-identifier-v4) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0623 - Accuracy: 0.9901 ## 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: 5e-05 - 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: 100 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.0005 | 1.0 | 219 | 0.0978 | 0.9820 | | 0.0003 | 2.0 | 438 | 0.0540 | 0.9892 | | 0.0025 | 3.0 | 657 | 0.0736 | 0.9860 | | 0.0000 | 4.0 | 876 | 0.0503 | 0.9919 | | 0.0003 | 5.0 | 1095 | 0.0623 | 0.9901 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.11.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2

Source context: 12 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo drrobot9/wav2vec2-nigerian-language-identifier-v5

Source context: 4 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo drrobot9/wav2vec2-nigerian-language-identifier-v5