metadata

license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - common_voice_16_0
metrics:
  - wer
model-index:
  - name: breeze-dsw-base-ml
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_16_0
          type: common_voice_16_0
          config: ml
          split: test
          args: ml
        metrics:
          - name: Wer
            type: wer
            value: 44.21686746987952

breeze-dsw-base-ml

This model is a fine-tuned version of openai/whisper-base on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.7354
Wer: 44.2169

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: 32
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
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
0.3151	4.02	200	0.4517	54.5134
0.0703	9.02	400	0.4561	46.7285
0.0144	14.02	600	0.5625	43.7627
0.006	19.02	800	0.6260	42.7247
0.0024	24.02	1000	0.6938	43.0306
0.0012	29.02	1200	0.7354	44.2169

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.16.2.dev0
Tokenizers 0.15.0