README.md

metadata

language:
  - ln
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Base Lingala - BrainTheos
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Fleurs
          type: google/fleurs
          config: ln_cd
          split: validation
          args: ln_cd
        metrics:
          - name: Wer
            type: wer
            value: 25.050916496945007

Whisper Base Lingala - BrainTheos

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

• Loss: 0.7265
• Wer: 25.0509

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: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0081	21.0	1000	0.6218	29.8710
0.0016	42.01	2000	0.6865	25.1188
0.0009	63.01	3000	0.7152	24.9151
0.0007	85.0	4000	0.7265	25.0509

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.12.1.dev0
• Tokenizers 0.13.3