metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_16_0
metrics:
  - wer
model-index:
  - name: breeze-listen-dsw-small-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: 34.38368860055607

breeze-listen-dsw-small-ml

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

Loss: 0.3647
Wer: 34.3837

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
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: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4577	1.02	100	0.4824	58.3874
0.1781	2.04	200	0.3066	41.0658
0.0935	3.06	300	0.2903	35.6441
0.057	5.0	400	0.3289	36.6172
0.0285	6.03	500	0.3425	35.3197
0.0203	7.05	600	0.3647	34.3837

Framework versions

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