metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- ml-superb-subset
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-ml-superb-xty
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ml-superb-subset
type: ml-superb-subset
config: xty
split: test
args: xty
metrics:
- name: Wer
type: wer
value: 1
wav2vec2-large-xls-r-300m-ml-superb-xty
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the ml-superb-subset dataset. It achieves the following results on the evaluation set:
- Loss: 3.2130
- Wer: 1.0
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
8.25 | 0.8219 | 30 | 6.0908 | 1.0 |
4.6254 | 1.6438 | 60 | 4.0849 | 1.0 |
3.87 | 2.4658 | 90 | 3.7436 | 1.0 |
3.6415 | 3.2877 | 120 | 3.5797 | 1.0 |
3.502 | 4.1096 | 150 | 3.4716 | 1.0 |
3.3476 | 4.9315 | 180 | 3.3731 | 1.0 |
3.2852 | 5.7534 | 210 | 3.3274 | 1.0 |
3.2806 | 6.5753 | 240 | 3.2766 | 1.0 |
3.1827 | 7.3973 | 270 | 3.2398 | 1.0 |
3.1649 | 8.2192 | 300 | 3.2373 | 1.0 |
3.1544 | 9.0411 | 330 | 3.2119 | 1.0 |
3.1401 | 9.8630 | 360 | 3.2130 | 1.0 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1