metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: b33-wav2vec2-large-xls-r-romansh-colab
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: rm-vallader
split: test
args: rm-vallader
metrics:
- name: Wer
type: wer
value: 0.24918490917559386
b33-wav2vec2-large-xls-r-romansh-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3035
- Wer: 0.2492
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
6.0706 | 6.06 | 400 | 2.9439 | 1.0 |
2.2123 | 12.12 | 800 | 0.4745 | 0.4308 |
0.2438 | 18.18 | 1200 | 0.3260 | 0.2855 |
0.1121 | 24.24 | 1600 | 0.3035 | 0.2492 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3