metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-slowakisch-home4
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: sk
split: test
args: sk
metrics:
- name: Wer
type: wer
value: 0.4326705560185736
wav2vec2-large-xls-r-300m-slowakisch-home4
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5308
- Wer: 0.4327
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.1691 | 2.44 | 400 | 3.1326 | 1.0 |
| 0.9673 | 4.88 | 800 | 0.6624 | 0.6227 |
| 0.3 | 7.32 | 1200 | 0.5933 | 0.4976 |
| 0.1571 | 9.76 | 1600 | 0.5308 | 0.4327 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3