wav2vec2-base-nsc-demo-2
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: 0.7769
- Wer: 0.2568
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: 32
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.95 | 6.67 | 20 | 1.0674 | 0.3160 |
0.6587 | 13.33 | 40 | 0.9156 | 0.2864 |
0.5063 | 20.0 | 60 | 0.8279 | 0.2741 |
0.3928 | 26.67 | 80 | 0.7769 | 0.2568 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 165
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for beatrice-yap/wav2vec2-base-nsc-demo-2
Base model
facebook/wav2vec2-base-960h