metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_9_0
metrics:
  - wer
model-index:
  - name: yt-special-batch88
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_9_0 id
          type: mozilla-foundation/common_voice_9_0
          config: id
          split: train
          args: id
        metrics:
          - name: Wer
            type: wer
            value: 5.357219480798112

yt-special-batch88

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:

Loss: 0.2602
Wer: 5.3572

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: 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
37.1656	1.58	1000	31.4152	569.1440
15.0344	3.17	2000	13.2072	144.3489
7.6075	4.75	3000	5.8946	42.3836
2.5225	6.34	4000	2.0158	19.5430
0.5364	7.92	5000	0.2602	5.3572

Framework versions

Transformers 4.31.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3