metadata

license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper small Sindhi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: sd_in
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 39.360351975632454

Whisper small Sindhi

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

Loss: 0.8761
Wer: 39.3604

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: 8
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_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: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0125	30.74	400	0.7639	43.5485
0.0007	61.52	800	0.8301	39.4873
0.0003	92.3	1200	0.8761	39.3604
0.0002	123.07	1600	0.8949	39.3604
0.0002	153.81	2000	0.9013	39.4196

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu117
Datasets 2.7.1
Tokenizers 0.13.2