--- language: - vi license: apache-2.0 base_model: openai/whisper-large-v3 tags: - hf-asr-leaderboard - generated_from_trainer datasets: - google/fleurs metrics: - wer model-index: - name: Whisper Large V3 Vi - Prateek Jain results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: google/fleurs type: google/fleurs config: vi_vn split: None args: 'config: vi, split: test' metrics: - name: Wer type: wer value: 218.83302440531355 --- # Whisper Large V3 Vi - Prateek Jain This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the google/fleurs dataset. It achieves the following results on the evaluation set: - Loss: 0.2355 - Wer: 218.8330 ## 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: 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: 250 - training_steps: 1500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.0148 | 2.66 | 500 | 0.2193 | 80.1012 | | 0.0014 | 5.32 | 1000 | 0.2275 | 247.5556 | | 0.0004 | 7.98 | 1500 | 0.2355 | 218.8330 | ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.0 - Tokenizers 0.15.1