metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-turkish-colab
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: tr
split: test
args: tr
metrics:
- name: Wer
type: wer
value: 0.7091714338438826
wav2vec2-large-xls-r-300m-turkish-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5247
- Wer: 0.7092
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1953 | 3.86 | 400 | 0.5740 | 0.7963 |
| 0.1959 | 7.73 | 800 | 0.5169 | 0.7743 |
| 0.1486 | 11.59 | 1200 | 0.5334 | 0.7501 |
| 0.1146 | 15.46 | 1600 | 0.5186 | 0.7226 |
| 0.0885 | 19.32 | 2000 | 0.5247 | 0.7092 |
Framework versions
- Transformers 4.36.1
- Pytorch 1.10.0+cu113
- Datasets 2.15.0
- Tokenizers 0.15.0