metadata

license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
datasets:
  - common_voice
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-jana-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice
          type: common_voice
          config: cy
          split: test
          args: cy
        metrics:
          - name: Wer
            type: wer
            value: 0.7846383810509371

wav2vec2-large-xls-r-300m-jana-colab

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:

Loss: 1.4528
Wer: 0.7846

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: 0.003
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: 300
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5925	1.67	200	1.4259	0.9056
1.1707	3.33	400	1.4610	0.9066
0.8991	5.0	600	1.3230	0.8607
0.6162	6.67	800	1.3388	0.8568
0.4192	8.33	1000	1.4365	0.8083
0.2729	10.0	1200	1.4528	0.7846

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3