metadata
license: apache-2.0
tags:
- automatic-speech-recognition
- w11wo/ljspeech_phonemes
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-ljspeech-gruut
results: []
wav2vec2-ljspeech-gruut
This model is a fine-tuned version of facebook/wav2vec2-base on the W11WO/LJSPEECH_PHONEMES - NA dataset. It achieves the following results on the evaluation set:
- Loss: 0.0683
- Wer: 0.0099
- Cer: 0.0058
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| No log | 1.0 | 348 | 2.2818 | 1.0 | 1.0 |
| 2.6692 | 2.0 | 696 | 0.2045 | 0.0527 | 0.0299 |
| 0.2225 | 3.0 | 1044 | 0.1162 | 0.0319 | 0.0189 |
| 0.2225 | 4.0 | 1392 | 0.0927 | 0.0235 | 0.0147 |
| 0.0868 | 5.0 | 1740 | 0.0797 | 0.0218 | 0.0143 |
| 0.0598 | 6.0 | 2088 | 0.0715 | 0.0197 | 0.0128 |
| 0.0598 | 7.0 | 2436 | 0.0652 | 0.0160 | 0.0103 |
| 0.0447 | 8.0 | 2784 | 0.0571 | 0.0152 | 0.0095 |
| 0.0368 | 9.0 | 3132 | 0.0608 | 0.0163 | 0.0112 |
| 0.0368 | 10.0 | 3480 | 0.0586 | 0.0137 | 0.0083 |
| 0.0303 | 11.0 | 3828 | 0.0641 | 0.0141 | 0.0085 |
| 0.0273 | 12.0 | 4176 | 0.0656 | 0.0131 | 0.0079 |
| 0.0232 | 13.0 | 4524 | 0.0690 | 0.0133 | 0.0082 |
| 0.0232 | 14.0 | 4872 | 0.0598 | 0.0128 | 0.0079 |
| 0.0189 | 15.0 | 5220 | 0.0671 | 0.0121 | 0.0074 |
| 0.017 | 16.0 | 5568 | 0.0654 | 0.0114 | 0.0069 |
| 0.017 | 17.0 | 5916 | 0.0751 | 0.0118 | 0.0073 |
| 0.0146 | 18.0 | 6264 | 0.0653 | 0.0112 | 0.0068 |
| 0.0127 | 19.0 | 6612 | 0.0682 | 0.0112 | 0.0069 |
| 0.0127 | 20.0 | 6960 | 0.0678 | 0.0114 | 0.0068 |
| 0.0114 | 21.0 | 7308 | 0.0656 | 0.0111 | 0.0066 |
| 0.0101 | 22.0 | 7656 | 0.0669 | 0.0109 | 0.0066 |
| 0.0092 | 23.0 | 8004 | 0.0677 | 0.0108 | 0.0065 |
| 0.0092 | 24.0 | 8352 | 0.0653 | 0.0104 | 0.0063 |
| 0.0088 | 25.0 | 8700 | 0.0673 | 0.0102 | 0.0063 |
| 0.0074 | 26.0 | 9048 | 0.0669 | 0.0105 | 0.0064 |
| 0.0074 | 27.0 | 9396 | 0.0707 | 0.0101 | 0.0061 |
| 0.0066 | 28.0 | 9744 | 0.0673 | 0.0100 | 0.0060 |
| 0.0058 | 29.0 | 10092 | 0.0689 | 0.0100 | 0.0059 |
| 0.0058 | 30.0 | 10440 | 0.0683 | 0.0099 | 0.0058 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.10.0
- Datasets 2.7.1
- Tokenizers 0.13.2