--- license: apache-2.0 tags: - generated_from_trainer datasets: - afrispeech-200 metrics: - wer model-index: - name: whisper-small-hi-2400_500_100 results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: afrispeech-200 type: afrispeech-200 config: all split: train args: all metrics: - name: Wer type: wer value: 0.6376484560570072 --- # whisper-small-hi-2400_500_100 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the afrispeech-200 dataset. It achieves the following results on the evaluation set: - Loss: 1.1136 - Wer: 0.6376 ## 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-06 - train_batch_size: 8 - 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: 200 - training_steps: 900 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | 2.0658 | 0.17 | 150 | 2.3108 | 1.0536 | | 1.4738 | 0.33 | 300 | 1.3138 | 1.0395 | | 0.8823 | 1.17 | 450 | 1.2148 | 0.7992 | | 1.1971 | 1.33 | 600 | 1.1466 | 0.7340 | | 0.7529 | 2.17 | 750 | 1.1256 | 0.6723 | | 1.1194 | 2.33 | 900 | 1.1136 | 0.6376 | ### Framework versions - Transformers 4.28.0.dev0 - Pytorch 1.13.1+cu116 - Datasets 2.10.1 - Tokenizers 0.13.2