w2v-bert-2.0-Chinese-colab-CV16.0-aishell-vtb-ark-gs-new_tokenizer
This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9612
- Wer: 1.0984
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Use paged_lion_8bit and the args are: No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.25
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.0072 | 0.2219 | 78 | 1.2166 | 1.1666 |
| 2.1247 | 0.4437 | 156 | 1.1178 | 1.1276 |
| 1.619 | 0.6656 | 234 | 1.0083 | 1.1015 |
| 1.7686 | 0.8875 | 312 | 0.9612 | 1.0984 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 2.17.1
- Tokenizers 0.21.0
- Downloads last month
- 18
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for urarik/w2v-bert-2.0-Chinese-colab-CV16.0-aishell-vtb-ark-gs-new_tokenizer
Base model
facebook/w2v-bert-2.0