metadata
base_model: ylacombe/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_16_0
metrics:
- wer
model-index:
- name: w2v-fine-tune-test-no-punct4
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_16_0
type: common_voice_16_0
config: tr
split: test
args: tr
metrics:
- name: Wer
type: wer
value: 0.436
w2v-fine-tune-test-no-punct4
This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7511
- Wer: 0.436
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.367 | 1.54 | 20 | 3.3453 | 1.0 |
| 2.1265 | 3.08 | 40 | 1.7730 | 0.996 |
| 0.4755 | 4.62 | 60 | 0.8654 | 0.684 |
| 0.203 | 6.15 | 80 | 0.7436 | 0.56 |
| 0.1251 | 7.69 | 100 | 0.8143 | 0.548 |
| 0.0449 | 9.23 | 120 | 0.7511 | 0.436 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0