metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - common_voice_7_0
metrics:
  - wer
base_model: facebook/w2v-bert-2.0
model-index:
  - name: w2v-bert-2.0-luganda-CV-train-validation-7.0
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: common_voice_7_0
          type: common_voice_7_0
          config: lg
          split: test
          args: lg
        metrics:
          - type: wer
            value: 0.18224972173115955
            name: Wer

w2v-bert-2.0-luganda-CV-train-validation-7.0

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_7_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2122
Wer: 0.1822

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: 32
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
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
1.31	1.89	300	0.2527	0.2845
0.112	3.77	600	0.2177	0.2326
0.0698	5.66	900	0.2085	0.2127
0.0426	7.55	1200	0.2024	0.1941
0.0272	9.43	1500	0.2122	0.1822

Framework versions

Transformers 4.38.1
Pytorch 2.2.1+cu121
Datasets 2.17.0
Tokenizers 0.15.2