metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- ./sample_speech.py
- generated_from_trainer
model-index:
- name: ko-xlsr5
results: []
ko-xlsr5
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the ./SAMPLE_SPEECH.PY - NA dataset. It achieves the following results on the evaluation set:
- Loss: 0.4067
- Cer: 0.1077
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.4452 | 0.97 | 1800 | 0.9257 | 0.2337 |
| 1.0684 | 1.95 | 3600 | 0.6873 | 0.1834 |
| 0.9269 | 2.92 | 5400 | 0.5857 | 0.1599 |
| 0.8264 | 3.9 | 7200 | 0.5357 | 0.1442 |
| 0.7637 | 4.87 | 9000 | 0.5069 | 0.1365 |
| 0.7033 | 5.85 | 10800 | 0.4744 | 0.1277 |
| 0.652 | 6.82 | 12600 | 0.4477 | 0.1210 |
| 0.5999 | 7.8 | 14400 | 0.4310 | 0.1144 |
| 0.5606 | 8.77 | 16200 | 0.4150 | 0.1114 |
| 0.5371 | 9.75 | 18000 | 0.4068 | 0.1085 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1