metadata
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: mms_que_gn_fine_tune
results: []
mms_que_gn_fine_tune
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: 0.2604
- Wer: 0.5340
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: 20
- 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: 100
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.2571 | 0.85 | 100 | 0.3938 | 0.6438 |
| 0.2939 | 1.71 | 200 | 0.2993 | 0.5681 |
| 0.2564 | 2.56 | 300 | 0.2752 | 0.5377 |
| 0.2235 | 3.42 | 400 | 0.2604 | 0.5340 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1