wav2vec2-large-mms-1b102-ckb_30cent
This model is a fine-tuned version of facebook/mms-1b-fl102 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3046
- Wer: 0.4115
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.1601 | 4.0988 | 500 | 0.3159 | 0.4227 |
| 0.5802 | 8.1975 | 1000 | 0.3046 | 0.4115 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0