metadata
base_model: ylacombe/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_16_0
metrics:
- wer
model-index:
- name: w2v-bert-2.0-mongolian-colab-CV16.0
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_16_0
type: common_voice_16_0
config: mn
split: test
args: mn
metrics:
- name: Wer
type: wer
value: 0.32330867957363496
w2v-bert-2.0-mongolian-colab-CV16.0
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: 0.5065
- Wer: 0.3233
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 |
|---|---|---|---|---|
| 3.8092 | 0.79 | 100 | 2.1220 | 1.0404 |
| 0.9265 | 1.58 | 200 | 0.7650 | 0.6125 |
| 0.5241 | 2.37 | 300 | 0.6422 | 0.5244 |
| 0.4165 | 3.16 | 400 | 0.6275 | 0.4711 |
| 0.3393 | 3.95 | 500 | 0.6290 | 0.4884 |
| 0.2664 | 4.74 | 600 | 0.5784 | 0.4712 |
| 0.2315 | 5.53 | 700 | 0.5370 | 0.4160 |
| 0.1819 | 6.32 | 800 | 0.5268 | 0.3813 |
| 0.1339 | 7.11 | 900 | 0.5100 | 0.3643 |
| 0.0993 | 7.91 | 1000 | 0.5368 | 0.3549 |
| 0.0739 | 8.7 | 1100 | 0.5405 | 0.3378 |
| 0.055 | 9.49 | 1200 | 0.5065 | 0.3233 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0