<!-- 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-base-timit-finetune
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 972.3115
- Wer: 1.0
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: 1000
- num_epochs: 60
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3325.1297 | 1.39 | 100 | 4054.7283 | 1.0 |
1624.4673 | 2.77 | 200 | 1100.8928 | 1.0 |
1079.3557 | 4.17 | 300 | 1009.5025 | 1.0 |
1026.4995 | 5.55 | 400 | 979.0 | 1.0 |
1005.6487 | 6.94 | 500 | 964.3292 | 1.0 |
1000.4138 | 8.33 | 600 | 972.3115 | 1.0 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1
- Datasets 2.7.0
- Tokenizers 0.11.0