metadata
tags:
- generated_from_trainer
datasets:
- common_voice_1_0
metrics:
- wer
model-index:
- name: fineturning-without-pretraining-3
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_1_0
type: common_voice_1_0
config: en
split: validation
args: en
metrics:
- name: Wer
type: wer
value: 1.231604810552179
fineturning-without-pretraining-3
This model is a fine-tuned version of on the common_voice_1_0 dataset. It achieves the following results on the evaluation set:
- Loss: 3.0417
- Wer: 1.2316
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: 32
- 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: 1000
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.4746 | 4.27 | 500 | 2.6868 | 1.0 |
| 2.5662 | 8.55 | 1000 | 2.4297 | 1.0371 |
| 2.3434 | 12.82 | 1500 | 2.3182 | 1.1941 |
| 2.134 | 17.09 | 2000 | 2.3792 | 1.1749 |
| 1.8502 | 21.37 | 2500 | 2.6371 | 1.1072 |
| 1.5697 | 25.64 | 3000 | 2.9421 | 1.1907 |
| 1.3814 | 29.91 | 3500 | 3.0417 | 1.2316 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2