<!-- 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. -->
faiq-wav2vec2-large-xlsr-indo-demo-RTX4090-vastai
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4110
- Wer: 0.4256
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: 0.0003
- 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: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
5.2358 | 2.92 | 400 | 2.7905 | 1.0 |
1.3455 | 5.84 | 800 | 0.4667 | 0.6305 |
0.3811 | 8.76 | 1200 | 0.4183 | 0.5335 |
0.2632 | 11.68 | 1600 | 0.3931 | 0.4883 |
0.2121 | 14.6 | 2000 | 0.3900 | 0.4693 |
0.1672 | 17.52 | 2400 | 0.3848 | 0.4560 |
0.1523 | 20.44 | 2800 | 0.3909 | 0.4485 |
0.13 | 23.36 | 3200 | 0.4030 | 0.4385 |
0.1188 | 26.28 | 3600 | 0.3963 | 0.4288 |
0.1065 | 29.2 | 4000 | 0.4110 | 0.4256 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.6.1
- Tokenizers 0.13.3