metadata
license: apache-2.0
base_model: facebook/wav2vec2-lv-60-espeak-cv-ft
tags:
- generated_from_trainer
datasets:
- nb_samtale
metrics:
- wer
model-index:
- name: cs2no-wav2vec2-large-xls-r-300m-cs-colab-phoneme
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: nb_samtale
type: nb_samtale
config: annotations
split: test
args: annotations
metrics:
- name: Wer
type: wer
value: 0.7063259628056816
cs2no-wav2vec2-large-xls-r-300m-cs-colab-phoneme
This model is a fine-tuned version of facebook/wav2vec2-lv-60-espeak-cv-ft on the nb_samtale dataset. It achieves the following results on the evaluation set:
- Loss: 4.9174
- Wer: 0.7063
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: 1e-05
- 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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.82 | 16.67 | 100 | 5.2819 | 0.7336 |
| 2.8834 | 33.33 | 200 | 4.9424 | 0.7091 |
| 2.5387 | 50.0 | 300 | 4.9174 | 0.7063 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0