README.md

metadata

language:
  - gn
license: apache-2.0
base_model: glob-asr/wav2vec2-large-xls-r-300m-guarani-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: Common Voice 16
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16
          type: mozilla-foundation/common_voice_16_1
          config: gn
          split: test
          args: gn
        metrics:
          - name: Wer
            type: wer
            value: 43.723554301833566

Common Voice 16

This model is a fine-tuned version of glob-asr/wav2vec2-large-xls-r-300m-guarani-small on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3202
• Wer: 43.7236

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4174	1.0101	100	0.3535	47.6728
0.3411	2.0202	200	0.3387	46.3188
0.2905	3.0303	300	0.3278	45.7546
0.2591	4.0404	400	0.3214	44.6544
0.251	5.0505	500	0.3202	43.7236

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1