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: 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: 0.5807
- Wer: 0.4336
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: 0.004
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.6531 | 1.0 | 20 | 7.3871 | 1.0 |
| 3.365 | 2.0 | 40 | 3.0972 | 1.0 |
| 2.3227 | 3.0 | 60 | 1.8379 | 0.8684 |
| 1.1025 | 4.0 | 80 | 0.9537 | 0.6287 |
| 0.8483 | 5.0 | 100 | 0.7576 | 0.5405 |
| 0.7097 | 6.0 | 120 | 0.6485 | 0.5041 |
| 0.659 | 7.0 | 140 | 0.6432 | 0.4912 |
| 0.5759 | 8.0 | 160 | 0.6042 | 0.4853 |
| 0.5178 | 9.0 | 180 | 0.5881 | 0.4630 |
| 0.4767 | 10.0 | 200 | 0.5807 | 0.4336 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0