metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-large-mms-1b-dzo-colab-3
results: []
wav2vec2-large-mms-1b-dzo-colab-3
This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6355
- Cer: 0.2026
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: Use OptimizerNames.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 | Cer |
|---|---|---|---|---|
| No log | 1.0 | 20 | 7.7865 | 0.9124 |
| No log | 2.0 | 40 | 3.0683 | 0.7195 |
| No log | 3.0 | 60 | 1.5908 | 0.3984 |
| No log | 4.0 | 80 | 1.0322 | 0.3041 |
| 4.2328 | 5.0 | 100 | 0.8169 | 0.2465 |
| 4.2328 | 6.0 | 120 | 0.7393 | 0.2348 |
| 4.2328 | 7.0 | 140 | 0.7103 | 0.2230 |
| 4.2328 | 8.0 | 160 | 0.6616 | 0.2154 |
| 4.2328 | 9.0 | 180 | 0.6547 | 0.2065 |
| 0.6749 | 10.0 | 200 | 0.6355 | 0.2026 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0