<!-- 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-large-xlsr-53_toy_train_fast_masked_augment_random_noise
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3471
- Wer: 0.4048
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: 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: 1000
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.0574 | 1.68 | 500 | 3.4185 | 0.9954 |
1.45 | 3.36 | 1000 | 0.7043 | 0.7171 |
0.8285 | 5.03 | 1500 | 0.3874 | 0.5050 |
0.668 | 6.71 | 2000 | 0.3321 | 0.4512 |
0.5324 | 8.39 | 2500 | 0.3394 | 0.4321 |
0.4775 | 10.07 | 3000 | 0.3533 | 0.4231 |
0.4421 | 11.74 | 3500 | 0.3487 | 0.4084 |
0.441 | 13.42 | 4000 | 0.3471 | 0.4048 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu102
- Datasets 2.1.0
- Tokenizers 0.12.1