Parakeet Ctc 1.1b Yoruba Lmhead

--- library_name: transformers language: - yo license: cc-by-4.0 base_model: nvidia/parakeet-ctc-1.1b tags: - generated_from_trainer metrics: - wer model-index: - name: EYEDOL/parakeet-ctc-1.1b-yoruba-lmhead results: [] --- # EYEDOL/parakeet-ctc-1.1b-yoruba-lmhead This model is a fine-tuned version of [nvidia/parakeet-ctc-1.1b](https://huggingface.co/nvidia/parakeet-ctc-1.1b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.3065 - Wer: 1.2131 ## 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: 16 - eval_batch_size: 32 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50 - training_steps: 1200 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:------:| | 19.8759 | 1.3605 | 200 | 8.1207 | 1.6099 | | 14.9688 | 2.7211 | 400 | 6.1871 | 1.5214 | | 12.7717 | 4.0816 | 600 | 4.9162 | 1.4126 | | 9.5410 | 5.4422 | 800 | 3.9930 | 1.3355 | | 7.3258 | 6.8027 | 1000 | 3.4915 | 1.3285 | | 7.1358 | 8.1633 | 1200 | 3.3065 | 1.2131 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.10.0+cu128 - Datasets 4.8.3 - Tokenizers 0.22.2