metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: facebook/wav2vec2-large-xlsr-53
datasets:
  - common_voice_16_1
metrics:
  - wer
model-index:
  - name: wav2vec2-common-voice-16_1_vi
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: common_voice_16_1
          type: common_voice_16_1
          config: vi
          split: None
          args: vi
        metrics:
          - type: wer
            value: 0.8006303375355835
            name: Wer

wav2vec2-common-voice-16_1_vi

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

Loss: 1.4738
Wer: 0.8006

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
17.2554	4.24	500	3.5535	1.0
3.4431	8.47	1000	3.3988	1.0
2.4492	12.71	1500	1.7446	1.0539
0.9214	16.95	2000	1.4497	0.8814
0.5148	21.19	2500	1.4543	0.8333
0.3619	25.42	3000	1.4791	0.8121
0.3003	29.66	3500	1.4738	0.8006

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2