metadata

language:
  - lg
license: apache-2.0
base_model: openai/whisper-small
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - tericlabs
metrics:
  - wer
model-index:
  - name: Whisper Small ganda
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Yogera data
          type: tericlabs
          config: lg
          split: test
          args: lg
        metrics:
          - name: Wer
            type: wer
            value: 54.276315789473685

Whisper Small ganda

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

Loss: 1.4937
Wer: 54.2763

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9882	26.0	500	1.4647	54.9342
0.0026	52.0	1000	1.3967	60.8553
0.0002	78.0	1500	1.4295	57.8947
0.0001	105.0	2000	1.4494	58.2237
0.0001	131.0	2500	1.4713	53.9474
0.0001	157.0	3000	1.4835	54.2763
0.0001	184.0	3500	1.4908	54.2763
0.0001	210.0	4000	1.4937	54.2763

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.16.0
Tokenizers 0.15.0