metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: tachiwin_totonac
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: ljcamargo--totonac_alpha_1
split: test
args: ljcamargo--totonac_alpha_1
metrics:
- name: Wer
type: wer
value: 0.689873417721519
tachiwin_totonac
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1224
- Wer: 0.6899
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: 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.1063 | 5.19 | 200 | 2.9834 | 1.0 |
| 2.9016 | 10.39 | 400 | 2.4405 | 0.9959 |
| 1.7606 | 15.58 | 600 | 1.1942 | 0.8532 |
| 1.0549 | 20.78 | 800 | 1.1132 | 0.7788 |
| 0.7553 | 25.97 | 1000 | 1.1224 | 0.6899 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3