metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: mms-1b-all-lg-CV-Fleurs-10hrs-v2
results: []
mms-1b-all-lg-CV-Fleurs-10hrs-v2
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: 0.2882
- Wer: 0.3573
- Cer: 0.0718
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 7.029 | 1.0 | 323 | 3.7469 | 1.0004 | 0.8729 |
| 2.0216 | 2.0 | 646 | 0.3238 | 0.3692 | 0.0766 |
| 0.3189 | 3.0 | 969 | 0.2733 | 0.3555 | 0.0727 |
| 0.2998 | 4.0 | 1292 | 0.2636 | 0.3509 | 0.0713 |
| 0.2919 | 5.0 | 1615 | 0.2587 | 0.3479 | 0.0715 |
| 0.2888 | 6.0 | 1938 | 0.2570 | 0.3470 | 0.0706 |
| 0.2876 | 7.0 | 2261 | 0.2636 | 0.3510 | 0.0708 |
| 0.3032 | 8.0 | 2584 | 0.2882 | 0.3573 | 0.0718 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0