README.md

metadata

language:
  - gn
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: Common Voice 16 - Guarani
    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: 58.90378171373863

Common Voice 16 - Guarani

This model is a fine-tuned version of openai/whisper-base on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5927
• Wer: 58.9038

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
2.3403	1.0101	100	0.9377	81.1872
0.5917	2.0202	200	0.6872	69.3633
0.3348	3.0303	300	0.6128	65.4380
0.2026	4.0404	400	0.5885	61.0340
0.1237	5.0505	500	0.5927	58.9038

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1