metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- vivos
metrics:
- wer
model-index:
- name: wav2vec2-vivos-asr
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: vivos
type: vivos
config: default
split: None
args: default
metrics:
- name: Wer
type: wer
value: 0.23381058715355313
wav2vec2-vivos-asr
This model is a fine-tuned version of facebook/wav2vec2-base on the vivos dataset. It achieves the following results on the evaluation set:
- Loss: 0.3492
- Wer: 0.2338
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.4226 | 2.0548 | 150 | 4.9423 | 1.0 |
| 3.59 | 4.1096 | 300 | 3.6898 | 1.0 |
| 3.4271 | 6.1644 | 450 | 3.5183 | 1.0 |
| 2.6948 | 8.2192 | 600 | 1.2770 | 0.8026 |
| 0.7372 | 10.2740 | 750 | 0.5197 | 0.3625 |
| 0.4012 | 12.3288 | 900 | 0.4108 | 0.2911 |
| 0.2974 | 14.3836 | 1050 | 0.3732 | 0.2604 |
| 0.2737 | 16.4384 | 1200 | 0.3550 | 0.2393 |
| 0.2108 | 18.4932 | 1350 | 0.3565 | 0.2434 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1