metadata
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: adapter_freezed_base_const_lr_1-e3
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: 0.9564916295314947
adapter_freezed_base_const_lr_1-e3
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: 1.0297
- Wer: 0.9565
- Cer: 0.2641
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: 0.001
- 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: constant
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.856 | 1.5385 | 500 | 0.9286 | 0.9535 | 0.2798 |
| 0.7189 | 3.0769 | 1000 | 0.8544 | 0.9296 | 0.2557 |
| 0.6114 | 4.6154 | 1500 | 0.9302 | 0.9596 | 0.2675 |
| 0.4397 | 6.1538 | 2000 | 0.9972 | 0.9294 | 0.2585 |
| 0.4507 | 7.6923 | 2500 | 0.9594 | 0.9363 | 0.2589 |
| 0.3154 | 9.2308 | 3000 | 1.0297 | 0.9565 | 0.2641 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1