metadata
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: w2v-bert-2.0-armenian-colab-CV17.0_10epochs
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: hy-AM
split: test
args: hy-AM
metrics:
- name: Wer
type: wer
value: 0.12119113573407202
w2v-bert-2.0-armenian-colab-CV17.0_10epochs
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1461
- Wer: 0.1212
- Cer: 0.0217
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
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.9136 | 1.0 | 325 | 0.2261 | 0.2817 | 0.0493 |
| 0.1872 | 2.0 | 650 | 0.1762 | 0.2208 | 0.0385 |
| 0.1168 | 3.0 | 975 | 0.1590 | 0.1807 | 0.0323 |
| 0.0817 | 4.0 | 1300 | 0.1444 | 0.1614 | 0.0287 |
| 0.058 | 5.0 | 1625 | 0.1414 | 0.1463 | 0.0259 |
| 0.0426 | 6.0 | 1950 | 0.1431 | 0.1447 | 0.0257 |
| 0.0284 | 7.0 | 2275 | 0.1333 | 0.1390 | 0.0251 |
| 0.0185 | 8.0 | 2600 | 0.1353 | 0.1254 | 0.0225 |
| 0.0114 | 9.0 | 2925 | 0.1434 | 0.1233 | 0.0219 |
| 0.007 | 10.0 | 3250 | 0.1461 | 0.1212 | 0.0217 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1