metadata
license: cc-by-nc-4.0
base_model: facebook/seamless-m4t-v2-large
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
model-index:
- name: seamless_turkish
results: []
seamless_turkish
This model is a fine-tuned version of facebook/seamless-m4t-v2-large on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8235
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7351 | 0.0215 | 1000 | 1.0948 |
| 1.845 | 0.0431 | 2000 | 0.9485 |
| 0.9842 | 0.0646 | 3000 | 0.8843 |
| 1.1293 | 0.0862 | 4000 | 0.8417 |
| 1.1266 | 0.1077 | 5000 | 0.8235 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1