metadata
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: wav2vec-commonvoice-1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: sw
split: test
args: sw
metrics:
- name: Wer
type: wer
value: 0.2989938400330582
wav2vec-commonvoice-1
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: inf
- Wer: 0.2990
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6465 | 1.0 | 918 | inf | 0.1938 |
| 0.5151 | 2.0 | 1836 | inf | 0.2995 |
| 0.5589 | 3.0 | 2754 | inf | 0.3003 |
| 0.5585 | 4.0 | 3672 | inf | 0.2999 |
| 0.5593 | 5.0 | 4590 | inf | 0.2990 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.4.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1