wav2vec2-large-mms-1b-korean-colab
This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0769
- Cer: 0.2387
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: 0.001
- train_batch_size: 8
- 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: 10
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.7655 | 1.58 | 60 | 1.5355 | 0.3132 |
| 0.8851 | 3.16 | 120 | 1.0769 | 0.2387 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5
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 Jungwonchang/wav2vec2-large-mms-1b-korean-colab
Base model
facebook/mms-1b-all