w2v-bert-2.0-malayalam-colab-CV16.0

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4547
  • Wer: 0.5301

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.0061 4.88 300 0.5145 0.6517
0.231 9.76 600 0.4547 0.5301

Framework versions

  • Transformers 4.37.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
71
Safetensors
Model size
606M params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Abhilashvj/w2v-bert-2.0-malayalam-colab-CV16.0

Finetuned
(253)
this model

Space using Abhilashvj/w2v-bert-2.0-malayalam-colab-CV16.0 1

Evaluation results