metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
datasets:
- fleurs
metrics:
- accuracy
model-index:
- name: wav2vec2-base-lang-id
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: google/fleurs
type: fleurs
config: bn_in
split: validation
args: bn_in
metrics:
- name: Accuracy
type: accuracy
value: 1
wav2vec2-base-lang-id
This model is a fine-tuned version of facebook/wav2vec2-base on the google/fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Accuracy: 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0001 | 1.0 | 94 | 0.0001 | 1.0 |
| 0.0001 | 2.0 | 188 | 0.0000 | 1.0 |
| 0.0 | 3.0 | 282 | 0.0000 | 1.0 |
| 0.0 | 4.0 | 376 | 0.0000 | 1.0 |
| 0.0 | 5.0 | 470 | 0.0000 | 1.0 |
| 0.0 | 6.0 | 564 | 0.0000 | 1.0 |
| 0.0 | 7.0 | 658 | 0.0000 | 1.0 |
| 0.0 | 8.0 | 752 | 0.0000 | 1.0 |
| 0.0 | 9.0 | 846 | 0.0000 | 1.0 |
| 0.0 | 10.0 | 940 | 0.0000 | 1.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.2.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1