kkkh_w2v2_large_finetune_teacher_babble_noise_mozilla_50_epochs_batch_16
This model is a fine-tuned version of facebook/wav2vec2-large-960h-lv60 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 24.1934
- Wer: 0.2500
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 4096
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
791.6482 | 8.78 | 150 | 30.5908 | 0.2961 |
509.9743 | 17.55 | 300 | 26.0843 | 0.2612 |
457.1243 | 26.33 | 450 | 25.0523 | 0.2562 |
432.307 | 35.11 | 600 | 24.4050 | 0.2510 |
420.762 | 43.89 | 750 | 24.1934 | 0.2500 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.