b30-wav2vec2-large-xls-r-romansh-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2906
- Wer: 0.2047
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
---|---|---|---|---|
6.1887 | 3.05 | 400 | 2.9441 | 1.0 |
2.3896 | 6.11 | 800 | 0.5913 | 0.5021 |
0.368 | 9.16 | 1200 | 0.3131 | 0.2834 |
0.1647 | 12.21 | 1600 | 0.2876 | 0.2531 |
0.1111 | 15.27 | 2000 | 0.2965 | 0.2494 |
0.0831 | 18.32 | 2400 | 0.2891 | 0.2264 |
0.0688 | 21.37 | 2800 | 0.2970 | 0.2259 |
0.0551 | 24.43 | 3200 | 0.2867 | 0.2075 |
0.0447 | 27.48 | 3600 | 0.2906 | 0.2047 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.