--- license: apache-2.0 tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-large-asr-th results: [] --- # wav2vec2-large-asr-th This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.3903 - Wer: 1.0 - Cer: 0.9442 ## 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: 0.0001 - train_batch_size: 16 - 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: 2000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |:-------------:|:-----:|:----:|:---------------:|:---:|:------:| | 3.9178 | 1.09 | 200 | 4.1261 | 1.0 | 1.0000 | | 3.7661 | 2.19 | 400 | 3.8671 | 1.0 | 1.0000 | | 3.7807 | 3.28 | 600 | 3.7873 | 1.0 | 1.0000 | | 3.7099 | 4.37 | 800 | 3.7331 | 1.0 | 1.0000 | | 3.4771 | 5.46 | 1000 | 3.3761 | 1.0 | 0.9998 | | 2.5528 | 6.56 | 1200 | 2.2584 | 1.0 | 0.9637 | | 1.9769 | 7.65 | 1400 | 1.7215 | 1.0 | 0.9507 | | 1.716 | 8.74 | 1600 | 1.5033 | 1.0 | 0.9464 | | 1.5803 | 9.84 | 1800 | 1.3903 | 1.0 | 0.9442 | | 1.4613 | 10.93 | 2000 | 1.3541 | 1.0 | 0.9433 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1+cu116 - Datasets 2.9.0 - Tokenizers 0.13.2