metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: csikasote/mms-1b-all-bemgen-combined-m50f50-62-DAT-0.06-fusion
tags:
- automatic-speech-recognition
- bemgen
- mms
- generated_from_trainer
model-index:
- name: mms-1b-all-bemgen-combined-m50f50-62-DAT-0.06-fusion
results: []
mms-1b-all-bemgen-combined-m50f50-62-DAT-0.06-fusion
This model is a fine-tuned version of csikasote/mms-1b-all-bemgen-combined-m50f50-62-DAT-0.06-fusion on the BEMGEN - FUS dataset. It achieves the following results on the evaluation set:
- Loss: 5.6905
- Cer: 0.9871
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 4
- seed: 62
- 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_ratio: 0.05
- lr_scheduler_warmup_steps: 100
- num_epochs: 30.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.0841 | 0.8439 | 100 | 3.0968 | 1.0 |
| 2.9431 | 1.6835 | 200 | 2.8880 | 1.0 |
| 2.9181 | 2.5232 | 300 | 2.8369 | 1.0 |
| 3.0592 | 3.3629 | 400 | 2.9964 | 1.0 |
| 2.8346 | 4.2025 | 500 | 2.8214 | 1.0 |
| 2.7789 | 5.0422 | 600 | 2.8139 | 1.0 |
| 2.8254 | 5.8861 | 700 | 2.8275 | 1.0 |
| 2.9289 | 6.7257 | 800 | 3.0263 | 1.0 |
| 5.4612 | 7.5654 | 900 | 5.6905 | 0.9871 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0